summaryrefslogtreecommitdiffstats
path: root/net
diff options
context:
space:
mode:
authorDaniel Baumann <daniel.baumann@progress-linux.org>2024-05-08 03:21:31 +0000
committerDaniel Baumann <daniel.baumann@progress-linux.org>2024-05-08 03:21:31 +0000
commit5dca02f2ee931aef66bb21dd8067c8b1af1e0d3e (patch)
tree6581b770eb1bd6cac1252a5451b89c092ea4c797 /net
parentAdding debian version 4.19.249-2. (diff)
downloadlinux-5dca02f2ee931aef66bb21dd8067c8b1af1e0d3e.tar.xz
linux-5dca02f2ee931aef66bb21dd8067c8b1af1e0d3e.zip
Merging upstream version 4.19.260.
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to '')
-rw-r--r--net/9p/client.c5
-rw-r--r--net/bluetooth/l2cap_core.c64
-rw-r--r--net/bluetooth/rfcomm/core.c50
-rw-r--r--net/bluetooth/rfcomm/sock.c46
-rw-r--r--net/bluetooth/sco.c30
-rw-r--r--net/bridge/br_netfilter_hooks.c23
-rw-r--r--net/bridge/br_netfilter_ipv6.c1
-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.c10
-rw-r--r--net/can/bcm.c18
-rw-r--r--net/core/dev.c14
-rw-r--r--net/core/filter.c1
-rw-r--r--net/core/neighbour.c27
-rw-r--r--net/core/skbuff.c2
-rw-r--r--net/core/sock.c2
-rw-r--r--net/core/sysctl_net_core.c15
-rw-r--r--net/dccp/proto.c10
-rw-r--r--net/ipv4/af_inet.c6
-rw-r--r--net/ipv4/cipso_ipv4.c12
-rw-r--r--net/ipv4/esp4.c5
-rw-r--r--net/ipv4/icmp.c10
-rw-r--r--net/ipv4/igmp.c47
-rw-r--r--net/ipv4/inetpeer.c12
-rw-r--r--net/ipv4/ip_gre.c15
-rw-r--r--net/ipv4/route.c2
-rw-r--r--net/ipv4/tcp.c12
-rw-r--r--net/ipv4/tcp_fastopen.c4
-rw-r--r--net/ipv4/tcp_input.c68
-rw-r--r--net/ipv4/tcp_ipv4.c2
-rw-r--r--net/ipv4/tcp_metrics.c5
-rw-r--r--net/ipv4/tcp_minisocks.c2
-rw-r--r--net/ipv4/tcp_output.c46
-rw-r--r--net/ipv4/tcp_recovery.c6
-rw-r--r--net/ipv4/tcp_timer.c14
-rw-r--r--net/ipv6/esp6.c5
-rw-r--r--net/ipv6/ip6_gre.c15
-rw-r--r--net/ipv6/ping.c6
-rw-r--r--net/ipv6/seg6.c5
-rw-r--r--net/ipv6/seg6_hmac.c1
-rw-r--r--net/ipv6/seg6_iptunnel.c5
-rw-r--r--net/ipv6/seg6_local.c2
-rw-r--r--net/ipv6/sit.c10
-rw-r--r--net/kcm/kcmsock.c15
-rw-r--r--net/key/af_key.c3
-rw-r--r--net/mac80211/ibss.c4
-rw-r--r--net/mac80211/scan.c11
-rw-r--r--net/mac802154/rx.c2
-rw-r--r--net/netfilter/Kconfig1
-rw-r--r--net/netfilter/nf_conntrack_irc.c39
-rw-r--r--net/netfilter/nf_conntrack_sip.c4
-rw-r--r--net/netfilter/nf_tables_api.c7
-rw-r--r--net/netfilter/nfnetlink_queue.c7
-rw-r--r--net/netfilter/nft_osf.c18
-rw-r--r--net/netfilter/nft_payload.c29
-rw-r--r--net/netfilter/nft_set_hash.c2
-rw-r--r--net/netfilter/nft_tunnel.c1
-rw-r--r--net/rds/ib_recv.c1
-rw-r--r--net/rose/af_rose.c11
-rw-r--r--net/rose/rose_loopback.c3
-rw-r--r--net/rose/rose_route.c6
-rw-r--r--net/rose/rose_timer.c34
-rw-r--r--net/rxrpc/local_object.c3
-rw-r--r--net/sched/cls_route.c12
-rw-r--r--net/sched/sch_generic.c7
-rw-r--r--net/sched/sch_netem.c4
-rw-r--r--net/sched/sch_sfb.c13
-rw-r--r--net/sctp/protocol.c2
-rw-r--r--net/sctp/stream_sched.c2
-rw-r--r--net/smc/af_smc.c1
-rw-r--r--net/socket.c2
-rw-r--r--net/sunrpc/backchannel_rqst.c14
-rw-r--r--net/sunrpc/xdr.c2
-rw-r--r--net/sunrpc/xprt.c4
-rw-r--r--net/tipc/monitor.c2
-rw-r--r--net/tipc/socket.c1
-rw-r--r--net/tls/tls_device.c8
-rw-r--r--net/vmw_vsock/af_vsock.c10
-rw-r--r--net/wireless/debugfs.c3
-rw-r--r--net/xfrm/xfrm_policy.c6
81 files changed, 597 insertions, 356 deletions
diff --git a/net/9p/client.c b/net/9p/client.c
index bb0a43b8a..98301add2 100644
--- a/net/9p/client.c
+++ b/net/9p/client.c
@@ -908,16 +908,13 @@ static struct p9_fid *p9_fid_create(struct p9_client *clnt)
struct p9_fid *fid;
p9_debug(P9_DEBUG_FID, "clnt %p\n", clnt);
- fid = kmalloc(sizeof(struct p9_fid), GFP_KERNEL);
+ fid = kzalloc(sizeof(struct p9_fid), GFP_KERNEL);
if (!fid)
return NULL;
- memset(&fid->qid, 0, sizeof(struct p9_qid));
fid->mode = -1;
fid->uid = current_fsuid();
fid->clnt = clnt;
- fid->rdir = NULL;
- fid->fid = 0;
idr_preload(GFP_KERNEL);
spin_lock_irq(&clnt->lock);
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index c0d64b414..65d20bdff 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -113,7 +113,8 @@ 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)
{
@@ -121,15 +122,19 @@ 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)
@@ -138,8 +143,12 @@ 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;
@@ -164,8 +173,12 @@ 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;
@@ -491,6 +504,16 @@ 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 %d", c, kref_read(&c->kref));
@@ -1781,11 +1804,11 @@ static struct l2cap_chan *l2cap_global_chan_by_psm(int state, __le16 psm,
bdaddr_t *dst,
u8 link_type)
{
- struct l2cap_chan *c, *c1 = NULL;
+ struct l2cap_chan *c, *tmp, *c1 = NULL;
read_lock(&chan_list_lock);
- list_for_each_entry(c, &chan_list, global_l) {
+ list_for_each_entry_safe(c, tmp, &chan_list, global_l) {
if (state && c->state != state)
continue;
@@ -1803,7 +1826,9 @@ 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);
+ if (!l2cap_chan_hold_unless_zero(c))
+ continue;
+
read_unlock(&chan_list_lock);
return c;
}
@@ -1818,7 +1843,7 @@ 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);
@@ -4204,6 +4229,7 @@ static inline int l2cap_config_req(struct l2cap_conn *conn,
unlock:
l2cap_chan_unlock(chan);
+ l2cap_chan_put(chan);
return err;
}
@@ -4316,6 +4342,7 @@ static inline int l2cap_config_rsp(struct l2cap_conn *conn,
done:
l2cap_chan_unlock(chan);
+ l2cap_chan_put(chan);
return err;
}
@@ -5044,6 +5071,7 @@ send_move_response:
l2cap_send_move_chan_rsp(chan, result);
l2cap_chan_unlock(chan);
+ l2cap_chan_put(chan);
return 0;
}
@@ -5136,6 +5164,7 @@ 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,
@@ -5165,6 +5194,7 @@ 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,
@@ -5228,6 +5258,7 @@ 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;
}
@@ -5263,6 +5294,7 @@ static inline int l2cap_move_channel_confirm_rsp(struct l2cap_conn *conn,
}
l2cap_chan_unlock(chan);
+ l2cap_chan_put(chan);
return 0;
}
@@ -5635,12 +5667,11 @@ 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;
@@ -5651,7 +5682,9 @@ 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;
}
@@ -6949,6 +6982,7 @@ drop:
done:
l2cap_chan_unlock(chan);
+ l2cap_chan_put(chan);
}
static void l2cap_conless_channel(struct l2cap_conn *conn, __le16 psm,
@@ -7353,7 +7387,7 @@ 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/rfcomm/core.c b/net/bluetooth/rfcomm/core.c
index b98225d65..e4eaf5d2a 100644
--- a/net/bluetooth/rfcomm/core.c
+++ b/net/bluetooth/rfcomm/core.c
@@ -552,22 +552,58 @@ struct rfcomm_dlc *rfcomm_dlc_exists(bdaddr_t *src, bdaddr_t *dst, u8 channel)
return dlc;
}
+static int rfcomm_dlc_send_frag(struct rfcomm_dlc *d, struct sk_buff *frag)
+{
+ int len = frag->len;
+
+ BT_DBG("dlc %p mtu %d len %d", d, d->mtu, len);
+
+ if (len > d->mtu)
+ return -EINVAL;
+
+ rfcomm_make_uih(frag, d->addr);
+ __skb_queue_tail(&d->tx_queue, frag);
+
+ return len;
+}
+
int rfcomm_dlc_send(struct rfcomm_dlc *d, struct sk_buff *skb)
{
- int len = skb->len;
+ unsigned long flags;
+ struct sk_buff *frag, *next;
+ int len;
if (d->state != BT_CONNECTED)
return -ENOTCONN;
- BT_DBG("dlc %p mtu %d len %d", d, d->mtu, len);
+ frag = skb_shinfo(skb)->frag_list;
+ skb_shinfo(skb)->frag_list = NULL;
- if (len > d->mtu)
- return -EINVAL;
+ /* Queue all fragments atomically. */
+ spin_lock_irqsave(&d->tx_queue.lock, flags);
- rfcomm_make_uih(skb, d->addr);
- skb_queue_tail(&d->tx_queue, skb);
+ len = rfcomm_dlc_send_frag(d, skb);
+ if (len < 0 || !frag)
+ goto unlock;
+
+ for (; frag; frag = next) {
+ int ret;
+
+ next = frag->next;
+
+ ret = rfcomm_dlc_send_frag(d, frag);
+ if (ret < 0) {
+ kfree_skb(frag);
+ goto unlock;
+ }
+
+ len += ret;
+ }
+
+unlock:
+ spin_unlock_irqrestore(&d->tx_queue.lock, flags);
- if (!test_bit(RFCOMM_TX_THROTTLED, &d->flags))
+ if (len > 0 && !test_bit(RFCOMM_TX_THROTTLED, &d->flags))
rfcomm_schedule();
return len;
}
diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c
index c044ff2f7..78830efe8 100644
--- a/net/bluetooth/rfcomm/sock.c
+++ b/net/bluetooth/rfcomm/sock.c
@@ -578,46 +578,20 @@ static int rfcomm_sock_sendmsg(struct socket *sock, struct msghdr *msg,
lock_sock(sk);
sent = bt_sock_wait_ready(sk, msg->msg_flags);
- if (sent)
- goto done;
-
- while (len) {
- size_t size = min_t(size_t, len, d->mtu);
- int err;
-
- skb = sock_alloc_send_skb(sk, size + RFCOMM_SKB_RESERVE,
- msg->msg_flags & MSG_DONTWAIT, &err);
- if (!skb) {
- if (sent == 0)
- sent = err;
- break;
- }
- skb_reserve(skb, RFCOMM_SKB_HEAD_RESERVE);
-
- err = memcpy_from_msg(skb_put(skb, size), msg, size);
- if (err) {
- kfree_skb(skb);
- if (sent == 0)
- sent = err;
- break;
- }
- skb->priority = sk->sk_priority;
+ release_sock(sk);
- err = rfcomm_dlc_send(d, skb);
- if (err < 0) {
- kfree_skb(skb);
- if (sent == 0)
- sent = err;
- break;
- }
+ if (sent)
+ return sent;
- sent += size;
- len -= size;
- }
+ skb = bt_skb_sendmmsg(sk, msg, len, d->mtu, RFCOMM_SKB_HEAD_RESERVE,
+ RFCOMM_SKB_TAIL_RESERVE);
+ if (IS_ERR(skb))
+ return PTR_ERR(skb);
-done:
- release_sock(sk);
+ sent = rfcomm_dlc_send(d, skb);
+ if (sent < 0)
+ kfree_skb(skb);
return sent;
}
diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c
index 14b5288d1..ee321d62b 100644
--- a/net/bluetooth/sco.c
+++ b/net/bluetooth/sco.c
@@ -279,12 +279,10 @@ static int sco_connect(struct hci_dev *hdev, struct sock *sk)
return err;
}
-static int sco_send_frame(struct sock *sk, void *buf, int len,
- unsigned int msg_flags)
+static int sco_send_frame(struct sock *sk, struct sk_buff *skb)
{
struct sco_conn *conn = sco_pi(sk)->conn;
- struct sk_buff *skb;
- int err;
+ int len = skb->len;
/* Check outgoing MTU */
if (len > conn->mtu)
@@ -292,11 +290,6 @@ static int sco_send_frame(struct sock *sk, void *buf, int len,
BT_DBG("sk %p len %d", sk, len);
- skb = bt_skb_send_alloc(sk, len, msg_flags & MSG_DONTWAIT, &err);
- if (!skb)
- return err;
-
- memcpy(skb_put(skb, len), buf, len);
hci_send_sco(conn->hcon, skb);
return len;
@@ -715,7 +708,7 @@ static int sco_sock_sendmsg(struct socket *sock, struct msghdr *msg,
size_t len)
{
struct sock *sk = sock->sk;
- void *buf;
+ struct sk_buff *skb;
int err;
BT_DBG("sock %p, sk %p", sock, sk);
@@ -727,24 +720,21 @@ static int sco_sock_sendmsg(struct socket *sock, struct msghdr *msg,
if (msg->msg_flags & MSG_OOB)
return -EOPNOTSUPP;
- buf = kmalloc(len, GFP_KERNEL);
- if (!buf)
- return -ENOMEM;
-
- if (memcpy_from_msg(buf, msg, len)) {
- kfree(buf);
- return -EFAULT;
- }
+ skb = bt_skb_sendmsg(sk, msg, len, len, 0, 0);
+ if (IS_ERR(skb))
+ return PTR_ERR(skb);
lock_sock(sk);
if (sk->sk_state == BT_CONNECTED)
- err = sco_send_frame(sk, buf, len, msg->msg_flags);
+ err = sco_send_frame(sk, skb);
else
err = -ENOTCONN;
release_sock(sk);
- kfree(buf);
+
+ if (err < 0)
+ kfree_skb(skb);
return err;
}
diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c
index 4b9d1d6bb..35642dc96 100644
--- a/net/bridge/br_netfilter_hooks.c
+++ b/net/bridge/br_netfilter_hooks.c
@@ -385,6 +385,7 @@ static int br_nf_pre_routing_finish(struct net *net, struct sock *sk, struct sk_
/* - Bridged-and-DNAT'ed traffic doesn't
* require ip_forwarding. */
if (rt->dst.dev == dev) {
+ skb_dst_drop(skb);
skb_dst_set(skb, &rt->dst);
goto bridged_dnat;
}
@@ -414,6 +415,7 @@ bridged_dnat:
kfree_skb(skb);
return 0;
}
+ skb_dst_drop(skb);
skb_dst_set_noref(skb, &rt->dst);
}
@@ -1001,9 +1003,24 @@ int br_nf_hook_thresh(unsigned int hook, struct net *net,
return okfn(net, sk, skb);
ops = nf_hook_entries_get_hook_ops(e);
- for (i = 0; i < e->num_hook_entries &&
- ops[i]->priority <= NF_BR_PRI_BRNF; i++)
- ;
+ for (i = 0; i < e->num_hook_entries; i++) {
+ /* These hooks have already been called */
+ if (ops[i]->priority < NF_BR_PRI_BRNF)
+ continue;
+
+ /* These hooks have not been called yet, run them. */
+ if (ops[i]->priority > NF_BR_PRI_BRNF)
+ break;
+
+ /* take a closer look at NF_BR_PRI_BRNF. */
+ if (ops[i]->hook == br_nf_pre_routing) {
+ /* This hook diverted the skb to this function,
+ * hooks after this have not been run yet.
+ */
+ i++;
+ break;
+ }
+ }
nf_hook_state_init(&state, hook, NFPROTO_BRIDGE, indev, outdev,
sk, net, okfn);
diff --git a/net/bridge/br_netfilter_ipv6.c b/net/bridge/br_netfilter_ipv6.c
index 09d5e0c7b..995d86777 100644
--- a/net/bridge/br_netfilter_ipv6.c
+++ b/net/bridge/br_netfilter_ipv6.c
@@ -201,6 +201,7 @@ static int br_nf_pre_routing_finish_ipv6(struct net *net, struct sock *sk, struc
kfree_skb(skb);
return 0;
}
+ skb_dst_drop(skb);
skb_dst_set_noref(skb, &rt->dst);
}
diff --git a/net/bridge/netfilter/ebtable_broute.c b/net/bridge/netfilter/ebtable_broute.c
index 276b60262..b21c8a317 100644
--- a/net/bridge/netfilter/ebtable_broute.c
+++ b/net/bridge/netfilter/ebtable_broute.c
@@ -33,18 +33,10 @@ 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 550324c51..c71795e4c 100644
--- a/net/bridge/netfilter/ebtable_filter.c
+++ b/net/bridge/netfilter/ebtable_filter.c
@@ -42,18 +42,10 @@ 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 c0fb3ca51..44dde9e63 100644
--- a/net/bridge/netfilter/ebtable_nat.c
+++ b/net/bridge/netfilter/ebtable_nat.c
@@ -42,18 +42,10 @@ 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 f59230e4f..59d8974ee 100644
--- a/net/bridge/netfilter/ebtables.c
+++ b/net/bridge/netfilter/ebtables.c
@@ -1003,9 +1003,10 @@ 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) {
+ ret = -EINVAL;
goto free_unlock;
+ }
if (repl->num_counters && repl->num_counters != t->private->nentries) {
ret = -EINVAL;
@@ -1197,11 +1198,6 @@ 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/can/bcm.c b/net/can/bcm.c
index 353098166..3c825b158 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -99,6 +99,7 @@ static inline u64 get_u64(const struct canfd_frame *cp, int offset)
struct bcm_op {
struct list_head list;
+ struct rcu_head rcu;
int ifindex;
canid_t can_id;
u32 flags;
@@ -717,10 +718,9 @@ static struct bcm_op *bcm_find_op(struct list_head *ops,
return NULL;
}
-static void bcm_remove_op(struct bcm_op *op)
+static void bcm_free_op_rcu(struct rcu_head *rcu_head)
{
- hrtimer_cancel(&op->timer);
- hrtimer_cancel(&op->thrtimer);
+ struct bcm_op *op = container_of(rcu_head, struct bcm_op, rcu);
if ((op->frames) && (op->frames != &op->sframe))
kfree(op->frames);
@@ -731,6 +731,14 @@ static void bcm_remove_op(struct bcm_op *op)
kfree(op);
}
+static void bcm_remove_op(struct bcm_op *op)
+{
+ hrtimer_cancel(&op->timer);
+ hrtimer_cancel(&op->thrtimer);
+
+ call_rcu(&op->rcu, bcm_free_op_rcu);
+}
+
static void bcm_rx_unreg(struct net_device *dev, struct bcm_op *op)
{
if (op->rx_reg_dev == dev) {
@@ -756,6 +764,9 @@ static int bcm_delete_rx_op(struct list_head *ops, struct bcm_msg_head *mh,
if ((op->can_id == mh->can_id) && (op->ifindex == ifindex) &&
(op->flags & CAN_FD_FRAME) == (mh->flags & CAN_FD_FRAME)) {
+ /* disable automatic timer on frame reception */
+ op->flags |= RX_NO_AUTOTIMER;
+
/*
* Don't care if we're bound or not (due to netdev
* problems) can_rx_unregister() is always a save
@@ -784,7 +795,6 @@ static int bcm_delete_rx_op(struct list_head *ops, struct bcm_msg_head *mh,
bcm_rx_handler, op);
list_del(&op->list);
- synchronize_rcu();
bcm_remove_op(op);
return 1; /* done */
}
diff --git a/net/core/dev.c b/net/core/dev.c
index 42f6ff8b9..880b096ee 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4474,7 +4474,7 @@ 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);
@@ -4794,7 +4794,7 @@ 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);
@@ -5146,7 +5146,7 @@ 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;
@@ -5176,7 +5176,7 @@ static 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);
@@ -5851,7 +5851,7 @@ 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;
@@ -6335,8 +6335,8 @@ 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);
diff --git a/net/core/filter.c b/net/core/filter.c
index c1310c9d1..5129e89f5 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4570,7 +4570,6 @@ static int bpf_push_seg6_encap(struct sk_buff *skb, u32 type, void *hdr, u32 len
if (err)
return err;
- ipv6_hdr(skb)->payload_len = htons(skb->len - sizeof(struct ipv6hdr));
skb_set_transport_header(skb, sizeof(struct ipv6hdr));
return seg6_lookup_nexthop(skb, NULL, 0);
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 6233e9856..73042407e 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -224,11 +224,26 @@ static int neigh_del_timer(struct neighbour *n)
return 0;
}
-static void pneigh_queue_purge(struct sk_buff_head *list)
+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;
- while ((skb = skb_dequeue(list)) != NULL) {
+ 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);
+ if (net == NULL || net_eq(dev_net(skb->dev), net)) {
+ __skb_unlink(skb, list);
+ __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);
}
@@ -297,9 +312,9 @@ int neigh_ifdown(struct neigh_table *tbl, struct net_device *dev)
write_lock_bh(&tbl->lock);
neigh_flush_dev(tbl, dev);
pneigh_ifdown_and_unlock(tbl, dev);
-
- del_timer_sync(&tbl->proxy_timer);
- pneigh_queue_purge(&tbl->proxy_queue);
+ pneigh_queue_purge(&tbl->proxy_queue, dev_net(dev));
+ if (skb_queue_empty_lockless(&tbl->proxy_queue))
+ del_timer_sync(&tbl->proxy_timer);
return 0;
}
EXPORT_SYMBOL(neigh_ifdown);
@@ -1614,7 +1629,7 @@ int neigh_table_clear(int index, struct neigh_table *tbl)
/* It is not clean... Fix it to unload IPv6 module safely */
cancel_delayed_work_sync(&tbl->gc_work);
del_timer_sync(&tbl->proxy_timer);
- pneigh_queue_purge(&tbl->proxy_queue);
+ pneigh_queue_purge(&tbl->proxy_queue, NULL);
neigh_ifdown(tbl, NULL);
if (atomic_read(&tbl->entries))
pr_crit("neighbour leakage\n");
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index c623c129d..e0be1f865 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -4377,7 +4377,7 @@ 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 79f085df5..cd23a8e45 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2856,7 +2856,7 @@ 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 = ~0U;
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index 0a0bf8062..d7e39167c 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -231,14 +231,17 @@ static int set_default_qdisc(struct ctl_table *table, int write,
static int proc_do_dev_weight(struct ctl_table *table, int write,
void __user *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/dccp/proto.c b/net/dccp/proto.c
index 43733accf..dbbcf50ae 100644
--- a/net/dccp/proto.c
+++ b/net/dccp/proto.c
@@ -769,11 +769,6 @@ int dccp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
lock_sock(sk);
- if (dccp_qpolicy_full(sk)) {
- rc = -EAGAIN;
- goto out_release;
- }
-
timeo = sock_sndtimeo(sk, noblock);
/*
@@ -792,6 +787,11 @@ int dccp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
if (skb == NULL)
goto out_release;
+ if (dccp_qpolicy_full(sk)) {
+ rc = -EAGAIN;
+ goto out_discard;
+ }
+
if (sk->sk_state == DCCP_CLOSED) {
rc = -ENOTCONN;
goto out_discard;
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index d8c222466..229519001 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -218,7 +218,7 @@ int inet_listen(struct socket *sock, int backlog)
* because the socket was in TCP_LISTEN state previously but
* was shutdown() rather than close().
*/
- tcp_fastopen = sock_net(sk)->ipv4.sysctl_tcp_fastopen;
+ tcp_fastopen = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fastopen);
if ((tcp_fastopen & TFO_SERVER_WO_SOCKOPT1) &&
(tcp_fastopen & TFO_SERVER_ENABLE) &&
!inet_csk(sk)->icsk_accept_queue.fastopenq.max_qlen) {
@@ -1209,7 +1209,7 @@ static int inet_sk_reselect_saddr(struct sock *sk)
if (new_saddr == old_saddr)
return 0;
- if (sock_net(sk)->ipv4.sysctl_ip_dynaddr > 1) {
+ if (READ_ONCE(sock_net(sk)->ipv4.sysctl_ip_dynaddr) > 1) {
pr_info("%s(): shifting inet->saddr from %pI4 to %pI4\n",
__func__, &old_saddr, &new_saddr);
}
@@ -1264,7 +1264,7 @@ int inet_sk_rebuild_header(struct sock *sk)
* Other protocols have to map its equivalent state to TCP_SYN_SENT.
* DCCP maps its DCCP_REQUESTING state to TCP_SYN_SENT. -acme
*/
- if (!sock_net(sk)->ipv4.sysctl_ip_dynaddr ||
+ if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_ip_dynaddr) ||
sk->sk_state != TCP_SYN_SENT ||
(sk->sk_userlocks & SOCK_BINDADDR_LOCK) ||
(err = inet_sk_reselect_saddr(sk)) != 0)
diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c
index e8b8dd1cb..8dcf9aec7 100644
--- a/net/ipv4/cipso_ipv4.c
+++ b/net/ipv4/cipso_ipv4.c
@@ -254,7 +254,7 @@ static int cipso_v4_cache_check(const unsigned char *key,
struct cipso_v4_map_cache_entry *prev_entry = NULL;
u32 hash;
- if (!cipso_v4_cache_enabled)
+ if (!READ_ONCE(cipso_v4_cache_enabled))
return -ENOENT;
hash = cipso_v4_map_cache_hash(key, key_len);
@@ -311,13 +311,14 @@ static int cipso_v4_cache_check(const unsigned char *key,
int cipso_v4_cache_add(const unsigned char *cipso_ptr,
const struct netlbl_lsm_secattr *secattr)
{
+ int bkt_size = READ_ONCE(cipso_v4_cache_bucketsize);
int ret_val = -EPERM;
u32 bkt;
struct cipso_v4_map_cache_entry *entry = NULL;
struct cipso_v4_map_cache_entry *old_entry = NULL;
u32 cipso_ptr_len;
- if (!cipso_v4_cache_enabled || cipso_v4_cache_bucketsize <= 0)
+ if (!READ_ONCE(cipso_v4_cache_enabled) || bkt_size <= 0)
return 0;
cipso_ptr_len = cipso_ptr[1];
@@ -337,7 +338,7 @@ int cipso_v4_cache_add(const unsigned char *cipso_ptr,
bkt = entry->hash & (CIPSO_V4_CACHE_BUCKETS - 1);
spin_lock_bh(&cipso_v4_cache[bkt].lock);
- if (cipso_v4_cache[bkt].size < cipso_v4_cache_bucketsize) {
+ if (cipso_v4_cache[bkt].size < bkt_size) {
list_add(&entry->list, &cipso_v4_cache[bkt].list);
cipso_v4_cache[bkt].size += 1;
} else {
@@ -1214,7 +1215,8 @@ static int cipso_v4_gentag_rbm(const struct cipso_v4_doi *doi_def,
/* This will send packets using the "optimized" format when
* possible as specified in section 3.4.2.6 of the
* CIPSO draft. */
- if (cipso_v4_rbm_optfmt && ret_val > 0 && ret_val <= 10)
+ if (READ_ONCE(cipso_v4_rbm_optfmt) && ret_val > 0 &&
+ ret_val <= 10)
tag_len = 14;
else
tag_len = 4 + ret_val;
@@ -1617,7 +1619,7 @@ int cipso_v4_validate(const struct sk_buff *skb, unsigned char **option)
* all the CIPSO validations here but it doesn't
* really specify _exactly_ what we need to validate
* ... so, just make it a sysctl tunable. */
- if (cipso_v4_rbm_strictvalid) {
+ if (READ_ONCE(cipso_v4_rbm_strictvalid)) {
if (cipso_v4_map_lvl_valid(doi_def,
tag[3]) < 0) {
err_offset = opt_iter + 3;
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 45bb5b60b..203569500 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -275,7 +275,6 @@ int esp_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *
struct page *page;
struct sk_buff *trailer;
int tailen = esp->tailen;
- unsigned int allocsz;
/* this is non-NULL only with UDP Encapsulation */
if (x->encap) {
@@ -285,8 +284,8 @@ int esp_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *
return err;
}
- allocsz = ALIGN(skb->data_len + tailen, L1_CACHE_BYTES);
- if (allocsz > ESP_SKB_FRAG_MAXSIZE)
+ if (ALIGN(tailen, L1_CACHE_BYTES) > PAGE_SIZE ||
+ ALIGN(skb->data_len, L1_CACHE_BYTES) > PAGE_SIZE)
goto cow;
if (!skb_cloned(skb)) {
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index fe10a565b..aa179e646 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -266,11 +266,12 @@ bool icmp_global_allow(void)
spin_lock(&icmp_global.lock);
delta = min_t(u32, now - icmp_global.stamp, HZ);
if (delta >= HZ / 50) {
- incr = sysctl_icmp_msgs_per_sec * delta / HZ ;
+ incr = READ_ONCE(sysctl_icmp_msgs_per_sec) * delta / HZ;
if (incr)
WRITE_ONCE(icmp_global.stamp, now);
}
- credit = min_t(u32, icmp_global.credit + incr, sysctl_icmp_msgs_burst);
+ credit = min_t(u32, icmp_global.credit + incr,
+ READ_ONCE(sysctl_icmp_msgs_burst));
if (credit) {
/* We want to use a credit of one in average, but need to randomize
* it for security reasons.
@@ -294,7 +295,7 @@ static bool icmpv4_mask_allow(struct net *net, int type, int code)
return true;
/* Limit if icmp type is enabled in ratemask. */
- if (!((1 << type) & net->ipv4.sysctl_icmp_ratemask))
+ if (!((1 << type) & READ_ONCE(net->ipv4.sysctl_icmp_ratemask)))
return true;
return false;
@@ -332,7 +333,8 @@ static bool icmpv4_xrlim_allow(struct net *net, struct rtable *rt,
vif = l3mdev_master_ifindex(dst->dev);
peer = inet_getpeer_v4(net->ipv4.peers, fl4->daddr, vif, 1);
- rc = inet_peer_xrlim_allow(peer, net->ipv4.sysctl_icmp_ratelimit);
+ rc = inet_peer_xrlim_allow(peer,
+ READ_ONCE(net->ipv4.sysctl_icmp_ratelimit));
if (peer)
inet_putpeer(peer);
out:
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index ee179e08d..a08acb54b 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -471,7 +471,8 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc,
if (pmc->multiaddr == IGMP_ALL_HOSTS)
return skb;
- if (ipv4_is_local_multicast(pmc->multiaddr) && !net->ipv4.sysctl_igmp_llm_reports)
+ if (ipv4_is_local_multicast(pmc->multiaddr) &&
+ !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports))
return skb;
mtu = READ_ONCE(dev->mtu);
@@ -597,7 +598,7 @@ static int igmpv3_send_report(struct in_device *in_dev, struct ip_mc_list *pmc)
if (pmc->multiaddr == IGMP_ALL_HOSTS)
continue;
if (ipv4_is_local_multicast(pmc->multiaddr) &&
- !net->ipv4.sysctl_igmp_llm_reports)
+ !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports))
continue;
spin_lock_bh(&pmc->lock);
if (pmc->sfcount[MCAST_EXCLUDE])
@@ -740,7 +741,8 @@ static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc,
if (type == IGMPV3_HOST_MEMBERSHIP_REPORT)
return igmpv3_send_report(in_dev, pmc);
- if (ipv4_is_local_multicast(group) && !net->ipv4.sysctl_igmp_llm_reports)
+ if (ipv4_is_local_multicast(group) &&
+ !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports))
return 0;
if (type == IGMP_HOST_LEAVE_MESSAGE)
@@ -829,7 +831,7 @@ static void igmp_ifc_event(struct in_device *in_dev)
struct net *net = dev_net(in_dev->dev);
if (IGMP_V1_SEEN(in_dev) || IGMP_V2_SEEN(in_dev))
return;
- WRITE_ONCE(in_dev->mr_ifc_count, in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv);
+ WRITE_ONCE(in_dev->mr_ifc_count, in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv));
igmp_ifc_start_timer(in_dev, 1);
}
@@ -924,7 +926,8 @@ static bool igmp_heard_report(struct in_device *in_dev, __be32 group)
if (group == IGMP_ALL_HOSTS)
return false;
- if (ipv4_is_local_multicast(group) && !net->ipv4.sysctl_igmp_llm_reports)
+ if (ipv4_is_local_multicast(group) &&
+ !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports))
return false;
rcu_read_lock();
@@ -1010,7 +1013,7 @@ static bool igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb,
* received value was zero, use the default or statically
* configured value.
*/
- in_dev->mr_qrv = ih3->qrv ?: net->ipv4.sysctl_igmp_qrv;
+ in_dev->mr_qrv = ih3->qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv);
in_dev->mr_qi = IGMPV3_QQIC(ih3->qqic)*HZ ?: IGMP_QUERY_INTERVAL;
/* RFC3376, 8.3. Query Response Interval:
@@ -1049,7 +1052,7 @@ static bool igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb,
if (im->multiaddr == IGMP_ALL_HOSTS)
continue;
if (ipv4_is_local_multicast(im->multiaddr) &&
- !net->ipv4.sysctl_igmp_llm_reports)
+ !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports))
continue;
spin_lock_bh(&im->lock);
if (im->tm_running)
@@ -1189,7 +1192,7 @@ static void igmpv3_add_delrec(struct in_device *in_dev, struct ip_mc_list *im)
pmc->interface = im->interface;
in_dev_hold(in_dev);
pmc->multiaddr = im->multiaddr;
- pmc->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv;
+ pmc->crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv);
pmc->sfmode = im->sfmode;
if (pmc->sfmode == MCAST_INCLUDE) {
struct ip_sf_list *psf;
@@ -1240,9 +1243,11 @@ static void igmpv3_del_delrec(struct in_device *in_dev, struct ip_mc_list *im)
swap(im->tomb, pmc->tomb);
swap(im->sources, pmc->sources);
for (psf = im->sources; psf; psf = psf->sf_next)
- psf->sf_crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv;
+ psf->sf_crcount = in_dev->mr_qrv ?:
+ READ_ONCE(net->ipv4.sysctl_igmp_qrv);
} else {
- im->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv;
+ im->crcount = in_dev->mr_qrv ?:
+ READ_ONCE(net->ipv4.sysctl_igmp_qrv);
}
in_dev_put(pmc->interface);
kfree_pmc(pmc);
@@ -1299,7 +1304,8 @@ static void igmp_group_dropped(struct ip_mc_list *im)
#ifdef CONFIG_IP_MULTICAST
if (im->multiaddr == IGMP_ALL_HOSTS)
return;
- if (ipv4_is_local_multicast(im->multiaddr) && !net->ipv4.sysctl_igmp_llm_reports)
+ if (ipv4_is_local_multicast(im->multiaddr) &&
+ !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports))
return;
reporter = im->reporter;
@@ -1336,13 +1342,14 @@ static void igmp_group_added(struct ip_mc_list *im)
#ifdef CONFIG_IP_MULTICAST
if (im->multiaddr == IGMP_ALL_HOSTS)
return;
- if (ipv4_is_local_multicast(im->multiaddr) && !net->ipv4.sysctl_igmp_llm_reports)
+ if (ipv4_is_local_multicast(im->multiaddr) &&
+ !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports))
return;
if (in_dev->dead)
return;
- im->unsolicit_count = net->ipv4.sysctl_igmp_qrv;
+ im->unsolicit_count = READ_ONCE(net->ipv4.sysctl_igmp_qrv);
if (IGMP_V1_SEEN(in_dev) || IGMP_V2_SEEN(in_dev)) {
spin_lock_bh(&im->lock);
igmp_start_timer(im, IGMP_INITIAL_REPORT_DELAY);
@@ -1356,7 +1363,7 @@ static void igmp_group_added(struct ip_mc_list *im)
* IN() to IN(A).
*/
if (im->sfmode == MCAST_EXCLUDE)
- im->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv;
+ im->crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv);
igmp_ifc_event(in_dev);
#endif
@@ -1657,7 +1664,7 @@ static void ip_mc_rejoin_groups(struct in_device *in_dev)
if (im->multiaddr == IGMP_ALL_HOSTS)
continue;
if (ipv4_is_local_multicast(im->multiaddr) &&
- !net->ipv4.sysctl_igmp_llm_reports)
+ !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports))
continue;
/* a failover is happening and switches
@@ -1764,7 +1771,7 @@ static void ip_mc_reset(struct in_device *in_dev)
in_dev->mr_qi = IGMP_QUERY_INTERVAL;
in_dev->mr_qri = IGMP_QUERY_RESPONSE_INTERVAL;
- in_dev->mr_qrv = net->ipv4.sysctl_igmp_qrv;
+ in_dev->mr_qrv = READ_ONCE(net->ipv4.sysctl_igmp_qrv);
}
#else
static void ip_mc_reset(struct in_device *in_dev)
@@ -1898,7 +1905,7 @@ static int ip_mc_del1_src(struct ip_mc_list *pmc, int sfmode,
#ifdef CONFIG_IP_MULTICAST
if (psf->sf_oldin &&
!IGMP_V1_SEEN(in_dev) && !IGMP_V2_SEEN(in_dev)) {
- psf->sf_crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv;
+ psf->sf_crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv);
psf->sf_next = pmc->tomb;
pmc->tomb = psf;
rv = 1;
@@ -1962,7 +1969,7 @@ static int ip_mc_del_src(struct in_device *in_dev, __be32 *pmca, int sfmode,
/* filter mode change */
pmc->sfmode = MCAST_INCLUDE;
#ifdef CONFIG_IP_MULTICAST
- pmc->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv;
+ pmc->crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv);
WRITE_ONCE(in_dev->mr_ifc_count, pmc->crcount);
for (psf = pmc->sources; psf; psf = psf->sf_next)
psf->sf_crcount = 0;
@@ -2141,7 +2148,7 @@ static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode,
#ifdef CONFIG_IP_MULTICAST
/* else no filters; keep old mode for reports */
- pmc->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv;
+ pmc->crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv);
WRITE_ONCE(in_dev->mr_ifc_count, pmc->crcount);
for (psf = pmc->sources; psf; psf = psf->sf_next)
psf->sf_crcount = 0;
@@ -2207,7 +2214,7 @@ static int __ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr,
count++;
}
err = -ENOBUFS;
- if (count >= net->ipv4.sysctl_igmp_max_memberships)
+ if (count >= READ_ONCE(net->ipv4.sysctl_igmp_max_memberships))
goto done;
iml = sock_kmalloc(sk, sizeof(*iml), GFP_KERNEL);
if (!iml)
diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c
index ff327a62c..a18668552 100644
--- a/net/ipv4/inetpeer.c
+++ b/net/ipv4/inetpeer.c
@@ -148,16 +148,20 @@ static void inet_peer_gc(struct inet_peer_base *base,
struct inet_peer *gc_stack[],
unsigned int gc_cnt)
{
+ int peer_threshold, peer_maxttl, peer_minttl;
struct inet_peer *p;
__u32 delta, ttl;
int i;
- if (base->total >= inet_peer_threshold)
+ peer_threshold = READ_ONCE(inet_peer_threshold);
+ peer_maxttl = READ_ONCE(inet_peer_maxttl);
+ peer_minttl = READ_ONCE(inet_peer_minttl);
+
+ if (base->total >= peer_threshold)
ttl = 0; /* be aggressive */
else
- ttl = inet_peer_maxttl
- - (inet_peer_maxttl - inet_peer_minttl) / HZ *
- base->total / inet_peer_threshold * HZ;
+ ttl = peer_maxttl - (peer_maxttl - peer_minttl) / HZ *
+ base->total / peer_threshold * HZ;
for (i = 0; i < gc_cnt; i++) {
p = gc_stack[i];
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index cf60d0e07..c72432ce9 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -574,7 +574,6 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev)
int tunnel_hlen;
int version;
int nhoff;
- int thoff;
tun_info = skb_tunnel_info(skb);
if (unlikely(!tun_info || !(tun_info->mode & IP_TUNNEL_INFO_TX) ||
@@ -609,10 +608,16 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev)
(ntohs(ip_hdr(skb)->tot_len) > skb->len - nhoff))
truncate = true;
- thoff = skb_transport_header(skb) - skb_mac_header(skb);
- if (skb->protocol == htons(ETH_P_IPV6) &&
- (ntohs(ipv6_hdr(skb)->payload_len) > skb->len - thoff))
- truncate = true;
+ if (skb->protocol == htons(ETH_P_IPV6)) {
+ int thoff;
+
+ if (skb_transport_header_was_set(skb))
+ thoff = skb_transport_header(skb) - skb_mac_header(skb);
+ else
+ thoff = nhoff + sizeof(struct ipv6hdr);
+ if (ntohs(ipv6_hdr(skb)->payload_len) > skb->len - thoff)
+ truncate = true;
+ }
if (version == 1) {
erspan_build_header(skb, ntohl(tunnel_id_to_key32(key->tun_id)),
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index d7f17581d..57e231652 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1419,7 +1419,7 @@ u32 ip_mtu_from_fib_result(struct fib_result *res, __be32 daddr)
struct net_device *dev = nh->nh_dev;
u32 mtu = 0;
- if (dev_net(dev)->ipv4.sysctl_ip_fwd_use_pmtu ||
+ if (READ_ONCE(dev_net(dev)->ipv4.sysctl_ip_fwd_use_pmtu) ||
fi->fib_metrics->metrics[RTAX_LOCK - 1] & (1 << RTAX_MTU))
mtu = fi->fib_mtu;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index f7795488b..768a7daab 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -436,7 +436,7 @@ void tcp_init_sock(struct sock *sk)
tp->snd_cwnd_clamp = ~0;
tp->mss_cache = TCP_MSS_DEFAULT;
- tp->reordering = sock_net(sk)->ipv4.sysctl_tcp_reordering;
+ tp->reordering = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reordering);
tcp_assign_congestion_control(sk);
tp->tsoffset = 0;
@@ -706,7 +706,7 @@ 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;
}
@@ -1160,7 +1160,8 @@ static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg,
struct sockaddr *uaddr = msg->msg_name;
int err, flags;
- if (!(sock_net(sk)->ipv4.sysctl_tcp_fastopen & TFO_CLIENT_ENABLE) ||
+ if (!(READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fastopen) &
+ TFO_CLIENT_ENABLE) ||
(uaddr && msg->msg_namelen >= sizeof(uaddr->sa_family) &&
uaddr->sa_family == AF_UNSPEC))
return -EOPNOTSUPP;
@@ -3056,7 +3057,8 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
case TCP_FASTOPEN_CONNECT:
if (val > 1 || val < 0) {
err = -EINVAL;
- } else if (net->ipv4.sysctl_tcp_fastopen & TFO_CLIENT_ENABLE) {
+ } else if (READ_ONCE(net->ipv4.sysctl_tcp_fastopen) &
+ TFO_CLIENT_ENABLE) {
if (sk->sk_state == TCP_CLOSE)
tp->fastopen_connect = val;
else
@@ -3386,7 +3388,7 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
case TCP_LINGER2:
val = tp->linger2;
if (val >= 0)
- val = (val ? : net->ipv4.sysctl_tcp_fin_timeout) / HZ;
+ val = (val ? : READ_ONCE(net->ipv4.sysctl_tcp_fin_timeout)) / HZ;
break;
case TCP_DEFER_ACCEPT:
val = retrans_to_secs(icsk->icsk_accept_queue.rskq_defer_accept,
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index 119d2c2f3..f726591de 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -313,7 +313,7 @@ static bool tcp_fastopen_no_cookie(const struct sock *sk,
const struct dst_entry *dst,
int flag)
{
- return (sock_net(sk)->ipv4.sysctl_tcp_fastopen & flag) ||
+ return (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fastopen) & flag) ||
tcp_sk(sk)->fastopen_no_cookie ||
(dst && dst_metric(dst, RTAX_FASTOPEN_NO_COOKIE));
}
@@ -328,7 +328,7 @@ struct sock *tcp_try_fastopen(struct sock *sk, struct sk_buff *skb,
const struct dst_entry *dst)
{
bool syn_data = TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq + 1;
- int tcp_fastopen = sock_net(sk)->ipv4.sysctl_tcp_fastopen;
+ int tcp_fastopen = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fastopen);
struct tcp_fastopen_cookie valid_foc = { .len = -1 };
struct sock *child;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 92f5068c7..aac5d5b73 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -432,7 +432,7 @@ static void tcp_grow_window(struct sock *sk, const struct sk_buff *skb)
*/
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;
@@ -893,7 +893,7 @@ static void tcp_check_sack_reordering(struct sock *sk, const u32 low_seq,
tp->undo_marker ? tp->undo_retrans : 0);
#endif
tp->reordering = min_t(u32, (metric + mss - 1) / mss,
- sock_net(sk)->ipv4.sysctl_tcp_max_reordering);
+ READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_max_reordering));
}
/* This exciting event is worth to be remembered. 8) */
@@ -1878,7 +1878,7 @@ static void tcp_check_reno_reordering(struct sock *sk, const int addend)
return;
tp->reordering = min_t(u32, tp->packets_out + addend,
- sock_net(sk)->ipv4.sysctl_tcp_max_reordering);
+ READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_max_reordering));
tp->reord_seen++;
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRENOREORDER);
}
@@ -1938,7 +1938,8 @@ static inline void tcp_init_undo(struct tcp_sock *tp)
static bool tcp_is_rack(const struct sock *sk)
{
- return sock_net(sk)->ipv4.sysctl_tcp_recovery & TCP_RACK_LOSS_DETECTION;
+ return READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_recovery) &
+ TCP_RACK_LOSS_DETECTION;
}
/* If we detect SACK reneging, forget all SACK information
@@ -1982,6 +1983,7 @@ void tcp_enter_loss(struct sock *sk)
struct tcp_sock *tp = tcp_sk(sk);
struct net *net = sock_net(sk);
bool new_recovery = icsk->icsk_ca_state < TCP_CA_Recovery;
+ u8 reordering;
tcp_timeout_mark_lost(sk);
@@ -2002,10 +2004,12 @@ void tcp_enter_loss(struct sock *sk)
/* Timeout in disordered state after receiving substantial DUPACKs
* suggests that the degree of reordering is over-estimated.
*/
+ reordering = READ_ONCE(net->ipv4.sysctl_tcp_reordering);
if (icsk->icsk_ca_state <= TCP_CA_Disorder &&
- tp->sacked_out >= net->ipv4.sysctl_tcp_reordering)
+ tp->sacked_out >= reordering)
tp->reordering = min_t(unsigned int, tp->reordering,
- net->ipv4.sysctl_tcp_reordering);
+ reordering);
+
tcp_set_ca_state(sk, TCP_CA_Loss);
tp->high_seq = tp->snd_nxt;
tcp_ecn_queue_cwr(tp);
@@ -2014,7 +2018,7 @@ 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;
}
@@ -2368,6 +2372,21 @@ static inline bool tcp_may_undo(const struct tcp_sock *tp)
return tp->undo_marker && (!tp->undo_retrans || tcp_packet_delayed(tp));
}
+static bool tcp_is_non_sack_preventing_reopen(struct sock *sk)
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+
+ if (tp->snd_una == tp->high_seq && tcp_is_reno(tp)) {
+ /* Hold old state until something *above* high_seq
+ * is ACKed. For Reno it is MUST to prevent false
+ * fast retransmits (RFC2582). SACK TCP is safe. */
+ if (!tcp_any_retrans_done(sk))
+ tp->retrans_stamp = 0;
+ return true;
+ }
+ return false;
+}
+
/* People celebrate: "We love our President!" */
static bool tcp_try_undo_recovery(struct sock *sk)
{
@@ -2390,14 +2409,8 @@ static bool tcp_try_undo_recovery(struct sock *sk)
} else if (tp->rack.reo_wnd_persist) {
tp->rack.reo_wnd_persist--;
}
- if (tp->snd_una == tp->high_seq && tcp_is_reno(tp)) {
- /* Hold old state until something *above* high_seq
- * is ACKed. For Reno it is MUST to prevent false
- * fast retransmits (RFC2582). SACK TCP is safe. */
- if (!tcp_any_retrans_done(sk))
- tp->retrans_stamp = 0;
+ if (tcp_is_non_sack_preventing_reopen(sk))
return true;
- }
tcp_set_ca_state(sk, TCP_CA_Open);
tp->is_sack_reneg = 0;
return false;
@@ -2433,6 +2446,8 @@ static bool tcp_try_undo_loss(struct sock *sk, bool frto_undo)
NET_INC_STATS(sock_net(sk),
LINUX_MIB_TCPSPURIOUSRTOS);
inet_csk(sk)->icsk_retransmits = 0;
+ if (tcp_is_non_sack_preventing_reopen(sk))
+ return true;
if (frto_undo || tcp_is_sack(tp)) {
tcp_set_ca_state(sk, TCP_CA_Open);
tp->is_sack_reneg = 0;
@@ -2899,7 +2914,7 @@ 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)) {
@@ -3303,7 +3318,8 @@ static inline bool tcp_may_raise_cwnd(const struct sock *sk, const int flag)
* new SACK or ECE mark may first advance cwnd here and later reduce
* cwnd in tcp_fastretrans_alert() based on more states.
*/
- if (tcp_sk(sk)->reordering > sock_net(sk)->ipv4.sysctl_tcp_reordering)
+ if (tcp_sk(sk)->reordering >
+ READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reordering))
return flag & FLAG_FORWARD_PROGRESS;
return flag & FLAG_DATA_ACKED;
@@ -3415,7 +3431,8 @@ 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! */
}
@@ -3462,11 +3479,11 @@ static void tcp_send_challenge_ack(struct sock *sk, const struct sk_buff *skb)
/* 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;
+ if (now != READ_ONCE(challenge_timestamp)) {
+ u32 ack_limit = READ_ONCE(net->ipv4.sysctl_tcp_challenge_ack_limit);
u32 half = (ack_limit + 1) >> 1;
- challenge_timestamp = now;
+ WRITE_ONCE(challenge_timestamp, now);
WRITE_ONCE(challenge_count, half + prandom_u32_max(ack_limit));
}
count = READ_ONCE(challenge_count);
@@ -4192,7 +4209,7 @@ 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))
@@ -4227,7 +4244,7 @@ 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;
if (after(TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt))
@@ -5233,7 +5250,7 @@ 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) {
@@ -5256,7 +5273,8 @@ 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(&tp->compressed_ack_timer, ns_to_ktime(delay),
@@ -5287,7 +5305,7 @@ static void tcp_check_urg(struct sock *sk, const struct tcphdr *th)
struct tcp_sock *tp = tcp_sk(sk);
u32 ptr = ntohs(th->urg_ptr);
- if (ptr && !sock_net(sk)->ipv4.sysctl_tcp_stdurg)
+ if (ptr && !READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_stdurg))
ptr--;
ptr += ntohl(th->seq);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 2719c60f2..ddc1af873 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -110,10 +110,10 @@ static u32 tcp_v4_init_ts_off(const struct net *net, const struct sk_buff *skb)
int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp)
{
+ int reuse = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_tw_reuse);
const struct inet_timewait_sock *tw = inet_twsk(sktw);
const struct tcp_timewait_sock *tcptw = tcp_twsk(sktw);
struct tcp_sock *tp = tcp_sk(sk);
- int reuse = sock_net(sk)->ipv4.sysctl_tcp_tw_reuse;
if (reuse == 2) {
/* Still does not detect *everything* that goes through
diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
index 03b51cdcc..4960e2b6b 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();
@@ -425,7 +425,8 @@ void tcp_update_metrics(struct sock *sk)
if (!tcp_metric_locked(tm, TCP_METRIC_REORDERING)) {
val = tcp_metric_get(tm, TCP_METRIC_REORDERING);
if (val < tp->reordering &&
- tp->reordering != net->ipv4.sysctl_tcp_reordering)
+ tp->reordering !=
+ READ_ONCE(net->ipv4.sysctl_tcp_reordering))
tcp_metric_set(tm, TCP_METRIC_REORDERING,
tp->reordering);
}
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index c79cb949d..0fc238d79 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -179,7 +179,7 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb,
* Oh well... nobody has a sufficient solution to this
* protocol bug yet.
*/
- if (twsk_net(tw)->ipv4.sysctl_tcp_rfc1337 == 0) {
+ if (!READ_ONCE(twsk_net(tw)->ipv4.sysctl_tcp_rfc1337)) {
kill:
inet_twsk_deschedule_put(tw);
return TCP_TW_SUCCESS;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 25dbdb27a..35bf58599 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1523,7 +1523,7 @@ void tcp_mtup_init(struct sock *sk)
struct inet_connection_sock *icsk = inet_csk(sk);
struct net *net = sock_net(sk);
- icsk->icsk_mtup.enabled = net->ipv4.sysctl_tcp_mtu_probing > 1;
+ icsk->icsk_mtup.enabled = READ_ONCE(net->ipv4.sysctl_tcp_mtu_probing) > 1;
icsk->icsk_mtup.search_high = tp->rx_opt.mss_clamp + sizeof(struct tcphdr) +
icsk->icsk_af_ops->net_header_len;
icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, net->ipv4.sysctl_tcp_base_mss);
@@ -1658,7 +1658,7 @@ static void tcp_cwnd_validate(struct sock *sk, bool is_cwnd_limited)
if (tp->packets_out > tp->snd_cwnd_used)
tp->snd_cwnd_used = tp->packets_out;
- if (sock_net(sk)->ipv4.sysctl_tcp_slow_start_after_idle &&
+ if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_slow_start_after_idle) &&
(s32)(tcp_jiffies32 - tp->snd_cwnd_stamp) >= inet_csk(sk)->icsk_rto &&
!ca_ops->cong_control)
tcp_cwnd_application_limited(sk);
@@ -1745,7 +1745,7 @@ 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);
@@ -2030,7 +2030,7 @@ static inline void tcp_mtu_check_reprobe(struct sock *sk)
u32 interval;
s32 delta;
- interval = net->ipv4.sysctl_tcp_probe_interval;
+ interval = READ_ONCE(net->ipv4.sysctl_tcp_probe_interval);
delta = tcp_jiffies32 - icsk->icsk_mtup.probe_timestamp;
if (unlikely(delta >= interval * HZ)) {
int mss = tcp_current_mss(sk);
@@ -2112,7 +2112,7 @@ static int tcp_mtu_probe(struct sock *sk)
* probing process by not resetting search range to its orignal.
*/
if (probe_size > tcp_mtu_to_mss(sk, icsk->icsk_mtup.search_high) ||
- interval < net->ipv4.sysctl_tcp_probe_threshold) {
+ interval < READ_ONCE(net->ipv4.sysctl_tcp_probe_threshold)) {
/* Check whether enough time has elaplased for
* another round of probing.
*/
@@ -2454,7 +2454,7 @@ bool tcp_schedule_loss_probe(struct sock *sk, bool advancing_rto)
if (tp->fastopen_rsk)
return false;
- early_retrans = sock_net(sk)->ipv4.sysctl_tcp_early_retrans;
+ early_retrans = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_early_retrans);
/* Schedule a loss probe in 2*RTT for SACK capable connections
* not in loss recovery, that are either limited by cwnd or application.
*/
@@ -2816,7 +2816,7 @@ static void tcp_retrans_try_collapse(struct sock *sk, struct sk_buff *to,
struct sk_buff *skb = to, *tmp;
bool first = true;
- if (!sock_net(sk)->ipv4.sysctl_tcp_retrans_collapse)
+ if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_retrans_collapse))
return;
if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)
return;
@@ -2856,7 +2856,7 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs)
struct tcp_sock *tp = tcp_sk(sk);
unsigned int cur_mss;
int diff, len, err;
-
+ int avail_wnd;
/* Inconclusive MTU probe */
if (icsk->icsk_mtup.probe_size)
@@ -2886,17 +2886,25 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs)
return -EHOSTUNREACH; /* Routing failure or similar. */
cur_mss = tcp_current_mss(sk);
+ avail_wnd = tcp_wnd_end(tp) - TCP_SKB_CB(skb)->seq;
/* If receiver has shrunk his window, and skb is out of
* new window, do not retransmit it. The exception is the
* case, when window is shrunk to zero. In this case
- * our retransmit serves as a zero window probe.
+ * our retransmit of one segment serves as a zero window probe.
*/
- if (!before(TCP_SKB_CB(skb)->seq, tcp_wnd_end(tp)) &&
- TCP_SKB_CB(skb)->seq != tp->snd_una)
- return -EAGAIN;
+ if (avail_wnd <= 0) {
+ if (TCP_SKB_CB(skb)->seq != tp->snd_una)
+ return -EAGAIN;
+ avail_wnd = cur_mss;
+ }
len = cur_mss * segs;
+ if (len > avail_wnd) {
+ len = rounddown(avail_wnd, cur_mss);
+ if (!len)
+ len = avail_wnd;
+ }
if (skb->len > len) {
if (tcp_fragment(sk, TCP_FRAG_IN_RTX_QUEUE, skb, len,
cur_mss, GFP_ATOMIC))
@@ -2910,8 +2918,9 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs)
diff -= tcp_skb_pcount(skb);
if (diff)
tcp_adjust_pcount(sk, skb, diff);
- if (skb->len < cur_mss)
- tcp_retrans_try_collapse(sk, skb, cur_mss);
+ avail_wnd = min_t(int, avail_wnd, cur_mss);
+ if (skb->len < avail_wnd)
+ tcp_retrans_try_collapse(sk, skb, avail_wnd);
}
/* RFC3168, section 6.1.1.1. ECN fallback */
@@ -3070,11 +3079,12 @@ void tcp_xmit_retransmit_queue(struct sock *sk)
*/
void sk_forced_mem_schedule(struct sock *sk, int size)
{
- int amt;
+ int delta, amt;
- if (size <= sk->sk_forward_alloc)
+ delta = size - sk->sk_forward_alloc;
+ if (delta <= 0)
return;
- amt = sk_mem_pages(size);
+ amt = sk_mem_pages(delta);
sk->sk_forward_alloc += amt * SK_MEM_QUANTUM;
sk_memory_allocated_add(sk, amt);
@@ -3776,7 +3786,7 @@ void tcp_send_probe0(struct sock *sk)
}
if (err <= 0) {
- if (icsk->icsk_backoff < net->ipv4.sysctl_tcp_retries2)
+ if (icsk->icsk_backoff < READ_ONCE(net->ipv4.sysctl_tcp_retries2))
icsk->icsk_backoff++;
icsk->icsk_probes_out++;
probe_max = TCP_RTO_MAX;
diff --git a/net/ipv4/tcp_recovery.c b/net/ipv4/tcp_recovery.c
index 0d96decba..61969bb93 100644
--- a/net/ipv4/tcp_recovery.c
+++ b/net/ipv4/tcp_recovery.c
@@ -33,7 +33,8 @@ static u32 tcp_rack_reo_wnd(const struct sock *sk)
return 0;
if (tp->sacked_out >= tp->reordering &&
- !(sock_net(sk)->ipv4.sysctl_tcp_recovery & TCP_RACK_NO_DUPTHRESH))
+ !(READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_recovery) &
+ TCP_RACK_NO_DUPTHRESH))
return 0;
}
@@ -203,7 +204,8 @@ void tcp_rack_update_reo_wnd(struct sock *sk, struct rate_sample *rs)
{
struct tcp_sock *tp = tcp_sk(sk);
- if (sock_net(sk)->ipv4.sysctl_tcp_recovery & TCP_RACK_STATIC_REO_WND ||
+ if ((READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_recovery) &
+ TCP_RACK_STATIC_REO_WND) ||
!rs->prior_delivered)
return;
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index d071ed6b8..84069db04 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -124,7 +124,7 @@ static int tcp_out_of_resources(struct sock *sk, bool do_reset)
*/
static int tcp_orphan_retries(struct sock *sk, bool alive)
{
- int retries = sock_net(sk)->ipv4.sysctl_tcp_orphan_retries; /* May be zero. */
+ int retries = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_orphan_retries); /* May be zero. */
/* We know from an ICMP that something is wrong. */
if (sk->sk_err_soft && !alive)
@@ -144,7 +144,7 @@ static void tcp_mtu_probing(struct inet_connection_sock *icsk, struct sock *sk)
int mss;
/* Black hole detection */
- if (!net->ipv4.sysctl_tcp_mtu_probing)
+ if (!READ_ONCE(net->ipv4.sysctl_tcp_mtu_probing))
return;
if (!icsk->icsk_mtup.enabled) {
@@ -226,7 +226,7 @@ static int tcp_write_timeout(struct sock *sk)
retry_until = icsk->icsk_syn_retries ? : net->ipv4.sysctl_tcp_syn_retries;
expired = icsk->icsk_retransmits >= retry_until;
} else {
- if (retransmits_timed_out(sk, net->ipv4.sysctl_tcp_retries1, 0)) {
+ if (retransmits_timed_out(sk, READ_ONCE(net->ipv4.sysctl_tcp_retries1), 0)) {
/* Black hole detection */
tcp_mtu_probing(icsk, sk);
@@ -235,7 +235,7 @@ static int tcp_write_timeout(struct sock *sk)
sk_rethink_txhash(sk);
}
- retry_until = net->ipv4.sysctl_tcp_retries2;
+ retry_until = READ_ONCE(net->ipv4.sysctl_tcp_retries2);
if (sock_flag(sk, SOCK_DEAD)) {
const bool alive = icsk->icsk_rto < TCP_RTO_MAX;
@@ -362,7 +362,7 @@ static void tcp_probe_timer(struct sock *sk)
(s32)(tcp_time_stamp(tp) - start_ts) > icsk->icsk_user_timeout)
goto abort;
- max_probes = sock_net(sk)->ipv4.sysctl_tcp_retries2;
+ max_probes = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_retries2);
if (sock_flag(sk, SOCK_DEAD)) {
const bool alive = inet_csk_rto_backoff(icsk, TCP_RTO_MAX) < TCP_RTO_MAX;
@@ -545,7 +545,7 @@ out_reset_timer:
* linear-timeout retransmissions into a black hole
*/
if (sk->sk_state == TCP_ESTABLISHED &&
- (tp->thin_lto || net->ipv4.sysctl_tcp_thin_linear_timeouts) &&
+ (tp->thin_lto || READ_ONCE(net->ipv4.sysctl_tcp_thin_linear_timeouts)) &&
tcp_stream_is_thin(tp) &&
icsk->icsk_retransmits <= TCP_THIN_LINEAR_RETRIES) {
icsk->icsk_backoff = 0;
@@ -556,7 +556,7 @@ out_reset_timer:
}
inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
tcp_clamp_rto_to_user_timeout(sk), TCP_RTO_MAX);
- if (retransmits_timed_out(sk, net->ipv4.sysctl_tcp_retries1 + 1, 0))
+ if (retransmits_timed_out(sk, READ_ONCE(net->ipv4.sysctl_tcp_retries1) + 1, 0))
__sk_dst_reset(sk);
out:;
diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c
index e3abfc97f..d847ffbe9 100644
--- a/net/ipv6/esp6.c
+++ b/net/ipv6/esp6.c
@@ -241,10 +241,9 @@ int esp6_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info
struct page *page;
struct sk_buff *trailer;
int tailen = esp->tailen;
- unsigned int allocsz;
- allocsz = ALIGN(skb->data_len + tailen, L1_CACHE_BYTES);
- if (allocsz > ESP_SKB_FRAG_MAXSIZE)
+ if (ALIGN(tailen, L1_CACHE_BYTES) > PAGE_SIZE ||
+ ALIGN(skb->data_len, L1_CACHE_BYTES) > PAGE_SIZE)
goto cow;
if (!skb_cloned(skb)) {
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 4fd6c0929..e617a98f4 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -946,7 +946,6 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb,
__be16 proto;
__u32 mtu;
int nhoff;
- int thoff;
if (!pskb_inet_may_pull(skb))
goto tx_err;
@@ -967,10 +966,16 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb,
(ntohs(ip_hdr(skb)->tot_len) > skb->len - nhoff))
truncate = true;
- thoff = skb_transport_header(skb) - skb_mac_header(skb);
- if (skb->protocol == htons(ETH_P_IPV6) &&
- (ntohs(ipv6_hdr(skb)->payload_len) > skb->len - thoff))
- truncate = true;
+ if (skb->protocol == htons(ETH_P_IPV6)) {
+ int thoff;
+
+ if (skb_transport_header_was_set(skb))
+ thoff = skb_transport_header(skb) - skb_mac_header(skb);
+ else
+ thoff = nhoff + sizeof(struct ipv6hdr);
+ if (ntohs(ipv6_hdr(skb)->payload_len) > skb->len - thoff)
+ truncate = true;
+ }
if (skb_cow_head(skb, dev->needed_headroom ?: t->hlen))
goto tx_err;
diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c
index 5c9be8594..23ae01715 100644
--- a/net/ipv6/ping.c
+++ b/net/ipv6/ping.c
@@ -27,6 +27,11 @@
#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)
@@ -170,6 +175,7 @@ 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/seg6.c b/net/ipv6/seg6.c
index 9b2f272ca..89d55770a 100644
--- a/net/ipv6/seg6.c
+++ b/net/ipv6/seg6.c
@@ -130,6 +130,11 @@ static int seg6_genl_sethmac(struct sk_buff *skb, struct genl_info *info)
goto out_unlock;
}
+ if (slen > nla_len(info->attrs[SEG6_ATTR_SECRET])) {
+ err = -EINVAL;
+ goto out_unlock;
+ }
+
if (hinfo) {
err = seg6_hmac_info_del(net, hmackeyid);
if (err)
diff --git a/net/ipv6/seg6_hmac.c b/net/ipv6/seg6_hmac.c
index a886a8f4c..b801283da 100644
--- a/net/ipv6/seg6_hmac.c
+++ b/net/ipv6/seg6_hmac.c
@@ -415,7 +415,6 @@ int __net_init seg6_hmac_net_init(struct net *net)
return 0;
}
-EXPORT_SYMBOL(seg6_hmac_net_init);
void seg6_hmac_exit(void)
{
diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c
index 26882fd93..2e9067285 100644
--- a/net/ipv6/seg6_iptunnel.c
+++ b/net/ipv6/seg6_iptunnel.c
@@ -176,6 +176,8 @@ int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto)
}
#endif
+ hdr->payload_len = htons(skb->len - sizeof(struct ipv6hdr));
+
skb_postpush_rcsum(skb, hdr, tot_len);
return 0;
@@ -228,6 +230,8 @@ int seg6_do_srh_inline(struct sk_buff *skb, struct ipv6_sr_hdr *osrh)
}
#endif
+ hdr->payload_len = htons(skb->len - sizeof(struct ipv6hdr));
+
skb_postpush_rcsum(skb, hdr, sizeof(struct ipv6hdr) + hdrlen);
return 0;
@@ -289,7 +293,6 @@ static int seg6_do_srh(struct sk_buff *skb)
break;
}
- ipv6_hdr(skb)->payload_len = htons(skb->len - sizeof(struct ipv6hdr));
skb_set_transport_header(skb, sizeof(struct ipv6hdr));
return 0;
diff --git a/net/ipv6/seg6_local.c b/net/ipv6/seg6_local.c
index 607709a88..18970f6a6 100644
--- a/net/ipv6/seg6_local.c
+++ b/net/ipv6/seg6_local.c
@@ -415,7 +415,6 @@ static int input_action_end_b6(struct sk_buff *skb, struct seg6_local_lwt *slwt)
if (err)
goto drop;
- ipv6_hdr(skb)->payload_len = htons(skb->len - sizeof(struct ipv6hdr));
skb_set_transport_header(skb, sizeof(struct ipv6hdr));
seg6_lookup_nexthop(skb, NULL, 0);
@@ -447,7 +446,6 @@ static int input_action_end_b6_encap(struct sk_buff *skb,
if (err)
goto drop;
- ipv6_hdr(skb)->payload_len = htons(skb->len - sizeof(struct ipv6hdr));
skb_set_transport_header(skb, sizeof(struct ipv6hdr));
seg6_lookup_nexthop(skb, NULL, 0);
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 55c999cbe..420b9fcc1 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -314,9 +314,7 @@ static int ipip6_tunnel_get_prl(struct ip_tunnel *t,
kcalloc(cmax, sizeof(*kp), GFP_KERNEL | __GFP_NOWARN) :
NULL;
- rcu_read_lock();
-
- ca = t->prl_count < cmax ? t->prl_count : cmax;
+ ca = min(t->prl_count, cmax);
if (!kp) {
/* We don't try hard to allocate much memory for
@@ -331,7 +329,7 @@ static int ipip6_tunnel_get_prl(struct ip_tunnel *t,
}
}
- c = 0;
+ rcu_read_lock();
for_each_prl_rcu(t->prl) {
if (c >= cmax)
break;
@@ -343,7 +341,7 @@ static int ipip6_tunnel_get_prl(struct ip_tunnel *t,
if (kprl.addr != htonl(INADDR_ANY))
break;
}
-out:
+
rcu_read_unlock();
len = sizeof(*kp) * c;
@@ -352,7 +350,7 @@ out:
ret = -EFAULT;
kfree(kp);
-
+out:
return ret;
}
diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c
index b919db02c..ef2543a4c 100644
--- a/net/kcm/kcmsock.c
+++ b/net/kcm/kcmsock.c
@@ -1412,12 +1412,6 @@ static int kcm_attach(struct socket *sock, struct socket *csock,
psock->sk = csk;
psock->bpf_prog = prog;
- err = strp_init(&psock->strp, csk, &cb);
- if (err) {
- kmem_cache_free(kcm_psockp, psock);
- goto out;
- }
-
write_lock_bh(&csk->sk_callback_lock);
/* Check if sk_user_data is aready by KCM or someone else.
@@ -1425,13 +1419,18 @@ static int kcm_attach(struct socket *sock, struct socket *csock,
*/
if (csk->sk_user_data) {
write_unlock_bh(&csk->sk_callback_lock);
- strp_stop(&psock->strp);
- strp_done(&psock->strp);
kmem_cache_free(kcm_psockp, psock);
err = -EALREADY;
goto out;
}
+ err = strp_init(&psock->strp, csk, &cb);
+ if (err) {
+ write_unlock_bh(&csk->sk_callback_lock);
+ kmem_cache_free(kcm_psockp, psock);
+ goto out;
+ }
+
psock->save_data_ready = csk->sk_data_ready;
psock->save_write_space = csk->sk_write_space;
psock->save_state_change = csk->sk_state_change;
diff --git a/net/key/af_key.c b/net/key/af_key.c
index af67e0d26..337c6bc82 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -1707,9 +1707,12 @@ 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/mac80211/ibss.c b/net/mac80211/ibss.c
index fa13eef25..38383b7e4 100644
--- a/net/mac80211/ibss.c
+++ b/net/mac80211/ibss.c
@@ -544,6 +544,10 @@ int ieee80211_ibss_finish_csa(struct ieee80211_sub_if_data *sdata)
sdata_assert_lock(sdata);
+ /* When not connected/joined, sending CSA doesn't make sense. */
+ if (ifibss->state != IEEE80211_IBSS_MLME_JOINED)
+ return -ENOLINK;
+
/* update cfg80211 bss information with the new channel */
if (!is_zero_ether_addr(ifibss->bssid)) {
cbss = cfg80211_get_bss(sdata->local->hw.wiphy,
diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c
index de42bcfed..e3d8be4fe 100644
--- a/net/mac80211/scan.c
+++ b/net/mac80211/scan.c
@@ -412,10 +412,6 @@ static void __ieee80211_scan_completed(struct ieee80211_hw *hw, bool aborted)
scan_req = rcu_dereference_protected(local->scan_req,
lockdep_is_held(&local->mtx));
- if (scan_req != local->int_scan_req) {
- local->scan_info.aborted = aborted;
- cfg80211_scan_done(scan_req, &local->scan_info);
- }
RCU_INIT_POINTER(local->scan_req, NULL);
scan_sdata = rcu_dereference_protected(local->scan_sdata,
@@ -425,6 +421,13 @@ static void __ieee80211_scan_completed(struct ieee80211_hw *hw, bool aborted)
local->scanning = 0;
local->scan_chandef.chan = NULL;
+ synchronize_rcu();
+
+ if (scan_req != local->int_scan_req) {
+ local->scan_info.aborted = aborted;
+ cfg80211_scan_done(scan_req, &local->scan_info);
+ }
+
/* Set power back to normal operating levels. */
ieee80211_hw_config(local, 0);
diff --git a/net/mac802154/rx.c b/net/mac802154/rx.c
index 4dcf6e185..060ccd0e1 100644
--- a/net/mac802154/rx.c
+++ b/net/mac802154/rx.c
@@ -52,7 +52,7 @@ ieee802154_subif_frame(struct ieee802154_sub_if_data *sdata,
switch (mac_cb(skb)->dest.mode) {
case IEEE802154_ADDR_NONE:
- if (mac_cb(skb)->dest.mode != IEEE802154_ADDR_NONE)
+ if (hdr->source.mode != IEEE802154_ADDR_NONE)
/* FIXME: check if we are PAN coordinator */
skb->pkt_type = PACKET_OTHERHOST;
else
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index 56cddadb6..92e0514f6 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -117,7 +117,6 @@ config NF_CONNTRACK_ZONES
config NF_CONNTRACK_PROCFS
bool "Supply CT list in procfs (OBSOLETE)"
- default y
depends on PROC_FS
---help---
This option enables for the list of known conntrack entries
diff --git a/net/netfilter/nf_conntrack_irc.c b/net/netfilter/nf_conntrack_irc.c
index 4099f4d79..23ead02c6 100644
--- a/net/netfilter/nf_conntrack_irc.c
+++ b/net/netfilter/nf_conntrack_irc.c
@@ -150,15 +150,37 @@ static int help(struct sk_buff *skb, unsigned int protoff,
data = ib_ptr;
data_limit = ib_ptr + skb->len - dataoff;
- /* strlen("\1DCC SENT t AAAAAAAA P\1\n")=24
- * 5+MINMATCHLEN+strlen("t AAAAAAAA P\1\n")=14 */
- while (data < data_limit - (19 + MINMATCHLEN)) {
- if (memcmp(data, "\1DCC ", 5)) {
+ /* Skip any whitespace */
+ while (data < data_limit - 10) {
+ if (*data == ' ' || *data == '\r' || *data == '\n')
+ data++;
+ else
+ break;
+ }
+
+ /* strlen("PRIVMSG x ")=10 */
+ if (data < data_limit - 10) {
+ if (strncasecmp("PRIVMSG ", data, 8))
+ goto out;
+ data += 8;
+ }
+
+ /* strlen(" :\1DCC SENT t AAAAAAAA P\1\n")=26
+ * 7+MINMATCHLEN+strlen("t AAAAAAAA P\1\n")=26
+ */
+ while (data < data_limit - (21 + MINMATCHLEN)) {
+ /* Find first " :", the start of message */
+ if (memcmp(data, " :", 2)) {
data++;
continue;
}
+ data += 2;
+
+ /* then check that place only for the DCC command */
+ if (memcmp(data, "\1DCC ", 5))
+ goto out;
data += 5;
- /* we have at least (19+MINMATCHLEN)-5 bytes valid data left */
+ /* we have at least (21+MINMATCHLEN)-(2+5) bytes valid data left */
iph = ip_hdr(skb);
pr_debug("DCC found in master %pI4:%u %pI4:%u\n",
@@ -174,7 +196,7 @@ static int help(struct sk_buff *skb, unsigned int protoff,
pr_debug("DCC %s detected\n", dccprotos[i]);
/* we have at least
- * (19+MINMATCHLEN)-5-dccprotos[i].matchlen bytes valid
+ * (21+MINMATCHLEN)-7-dccprotos[i].matchlen bytes valid
* data left (== 14/13 bytes) */
if (parse_dcc(data, data_limit, &dcc_ip,
&dcc_port, &addr_beg_p, &addr_end_p)) {
@@ -187,8 +209,9 @@ static int help(struct sk_buff *skb, unsigned int protoff,
/* dcc_ip can be the internal OR external (NAT'ed) IP */
tuple = &ct->tuplehash[dir].tuple;
- if (tuple->src.u3.ip != dcc_ip &&
- tuple->dst.u3.ip != dcc_ip) {
+ if ((tuple->src.u3.ip != dcc_ip &&
+ ct->tuplehash[!dir].tuple.dst.u3.ip != dcc_ip) ||
+ dcc_port == 0) {
net_warn_ratelimited("Forged DCC command from %pI4: %pI4:%u\n",
&tuple->src.u3.ip,
&dcc_ip, dcc_port);
diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c
index c8d2b6688..046f118de 100644
--- a/net/netfilter/nf_conntrack_sip.c
+++ b/net/netfilter/nf_conntrack_sip.c
@@ -471,7 +471,7 @@ static int ct_sip_walk_headers(const struct nf_conn *ct, const char *dptr,
return ret;
if (ret == 0)
break;
- dataoff += *matchoff;
+ dataoff = *matchoff;
}
*in_header = 0;
}
@@ -483,7 +483,7 @@ static int ct_sip_walk_headers(const struct nf_conn *ct, const char *dptr,
break;
if (ret == 0)
return ret;
- dataoff += *matchoff;
+ dataoff = *matchoff;
}
if (in_header)
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index ab68076d2..079f76849 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -96,6 +96,7 @@ static struct nft_trans *nft_trans_alloc_gfp(const struct nft_ctx *ctx,
if (trans == NULL)
return NULL;
+ INIT_LIST_HEAD(&trans->list);
trans->msg_type = msg_type;
trans->ctx = *ctx;
@@ -3039,6 +3040,7 @@ static struct nft_set *nft_set_lookup_byhandle(const struct nft_table *table,
}
static struct nft_set *nft_set_lookup_byid(const struct net *net,
+ const struct nft_table *table,
const struct nlattr *nla, u8 genmask)
{
struct nft_trans *trans;
@@ -3049,6 +3051,7 @@ static struct nft_set *nft_set_lookup_byid(const struct net *net,
struct nft_set *set = nft_trans_set(trans);
if (id == nft_trans_set_id(trans) &&
+ set->table == table &&
nft_active_genmask(set, genmask))
return set;
}
@@ -3069,7 +3072,7 @@ struct nft_set *nft_set_lookup_global(const struct net *net,
if (!nla_set_id)
return set;
- set = nft_set_lookup_byid(net, nla_set_id, genmask);
+ set = nft_set_lookup_byid(net, table, nla_set_id, genmask);
}
return set;
}
@@ -3095,7 +3098,7 @@ cont:
list_for_each_entry(i, &ctx->table->sets, list) {
int tmp;
- if (!nft_is_active_next(ctx->net, set))
+ if (!nft_is_active_next(ctx->net, i))
continue;
if (!sscanf(i->name, name, &tmp))
continue;
diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c
index a5aff2834..cd496b074 100644
--- a/net/netfilter/nfnetlink_queue.c
+++ b/net/netfilter/nfnetlink_queue.c
@@ -850,11 +850,16 @@ 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_osf.c b/net/netfilter/nft_osf.c
index e259454b6..4fac2d9a4 100644
--- a/net/netfilter/nft_osf.c
+++ b/net/netfilter/nft_osf.c
@@ -81,9 +81,21 @@ 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 struct nft_expr_type nft_osf_type;
diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c
index fd87216bc..5732b32ab 100644
--- a/net/netfilter/nft_payload.c
+++ b/net/netfilter/nft_payload.c
@@ -332,6 +332,8 @@ 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]));
@@ -339,11 +341,15 @@ static int nft_payload_set_init(const struct nft_ctx *ctx,
priv->sreg = nft_parse_register(tb[NFTA_PAYLOAD_SREG]);
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;
@@ -354,13 +360,14 @@ 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;
default:
return -EOPNOTSUPP;
}
+ priv->csum_type = csum_type;
return nft_validate_register_load(priv->sreg, priv->len);
}
@@ -398,6 +405,7 @@ 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 ||
@@ -423,8 +431,13 @@ 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)
diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c
index dbc4ed643..0b8510a41 100644
--- a/net/netfilter/nft_set_hash.c
+++ b/net/netfilter/nft_set_hash.c
@@ -145,6 +145,7 @@ static bool nft_rhash_update(struct nft_set *set, const u32 *key,
/* Another cpu may race to insert the element with the same key */
if (prev) {
nft_set_elem_destroy(set, he, true);
+ atomic_dec(&set->nelems);
he = prev;
}
@@ -154,6 +155,7 @@ out:
err2:
nft_set_elem_destroy(set, he, true);
+ atomic_dec(&set->nelems);
err1:
return false;
}
diff --git a/net/netfilter/nft_tunnel.c b/net/netfilter/nft_tunnel.c
index 8ae948fd9..3fc55c81f 100644
--- a/net/netfilter/nft_tunnel.c
+++ b/net/netfilter/nft_tunnel.c
@@ -104,6 +104,7 @@ 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/rds/ib_recv.c b/net/rds/ib_recv.c
index 2f16146e4..18e0e3cba 100644
--- a/net/rds/ib_recv.c
+++ b/net/rds/ib_recv.c
@@ -362,6 +362,7 @@ static int acquire_refill(struct rds_connection *conn)
static void release_refill(struct rds_connection *conn)
{
clear_bit(RDS_RECV_REFILL, &conn->c_flags);
+ smp_mb__after_atomic();
/* We don't use wait_on_bit()/wake_up_bit() because our waking is in a
* hot path and finding waiters is very rare. We don't want to walk
diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c
index d00a0ef39..03a1ee221 100644
--- a/net/rose/af_rose.c
+++ b/net/rose/af_rose.c
@@ -194,6 +194,7 @@ static void rose_kill_by_device(struct net_device *dev)
rose_disconnect(s, ENETUNREACH, ROSE_OUT_OF_ORDER, 0);
if (rose->neighbour)
rose->neighbour->use--;
+ dev_put(rose->device);
rose->device = NULL;
}
}
@@ -594,6 +595,8 @@ static struct sock *rose_make_new(struct sock *osk)
rose->idle = orose->idle;
rose->defer = orose->defer;
rose->device = orose->device;
+ if (rose->device)
+ dev_hold(rose->device);
rose->qbitincl = orose->qbitincl;
return sk;
@@ -647,6 +650,7 @@ static int rose_release(struct socket *sock)
break;
}
+ dev_put(rose->device);
sock->sk = NULL;
release_sock(sk);
sock_put(sk);
@@ -721,7 +725,6 @@ static int rose_connect(struct socket *sock, struct sockaddr *uaddr, int addr_le
struct rose_sock *rose = rose_sk(sk);
struct sockaddr_rose *addr = (struct sockaddr_rose *)uaddr;
unsigned char cause, diagnostic;
- struct net_device *dev;
ax25_uid_assoc *user;
int n, err = 0;
@@ -778,9 +781,12 @@ static int rose_connect(struct socket *sock, struct sockaddr *uaddr, int addr_le
}
if (sock_flag(sk, SOCK_ZAPPED)) { /* Must bind first - autobinding in this may or may not work */
+ struct net_device *dev;
+
sock_reset_flag(sk, SOCK_ZAPPED);
- if ((dev = rose_dev_first()) == NULL) {
+ dev = rose_dev_first();
+ if (!dev) {
err = -ENETUNREACH;
goto out_release;
}
@@ -788,6 +794,7 @@ static int rose_connect(struct socket *sock, struct sockaddr *uaddr, int addr_le
user = ax25_findbyuid(current_euid());
if (!user) {
err = -EINVAL;
+ dev_put(dev);
goto out_release;
}
diff --git a/net/rose/rose_loopback.c b/net/rose/rose_loopback.c
index c318e5c9f..56eea298b 100644
--- a/net/rose/rose_loopback.c
+++ b/net/rose/rose_loopback.c
@@ -99,7 +99,8 @@ 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/rose/rose_route.c b/net/rose/rose_route.c
index f2ff21d7d..5671853be 100644
--- a/net/rose/rose_route.c
+++ b/net/rose/rose_route.c
@@ -230,8 +230,8 @@ static void rose_remove_neigh(struct rose_neigh *rose_neigh)
{
struct rose_neigh *s;
- rose_stop_ftimer(rose_neigh);
- rose_stop_t0timer(rose_neigh);
+ del_timer_sync(&rose_neigh->ftimer);
+ del_timer_sync(&rose_neigh->t0timer);
skb_queue_purge(&rose_neigh->queue);
@@ -616,6 +616,8 @@ struct net_device *rose_dev_first(void)
if (first == NULL || strncmp(dev->name, first->name, 3) < 0)
first = dev;
}
+ if (first)
+ dev_hold(first);
rcu_read_unlock();
return first;
diff --git a/net/rose/rose_timer.c b/net/rose/rose_timer.c
index 74555fb95..cede9d0ce 100644
--- a/net/rose/rose_timer.c
+++ b/net/rose/rose_timer.c
@@ -34,89 +34,89 @@ static void rose_idletimer_expiry(struct timer_list *);
void rose_start_heartbeat(struct sock *sk)
{
- del_timer(&sk->sk_timer);
+ sk_stop_timer(sk, &sk->sk_timer);
sk->sk_timer.function = rose_heartbeat_expiry;
sk->sk_timer.expires = jiffies + 5 * HZ;
- add_timer(&sk->sk_timer);
+ sk_reset_timer(sk, &sk->sk_timer, sk->sk_timer.expires);
}
void rose_start_t1timer(struct sock *sk)
{
struct rose_sock *rose = rose_sk(sk);
- del_timer(&rose->timer);
+ sk_stop_timer(sk, &rose->timer);
rose->timer.function = rose_timer_expiry;
rose->timer.expires = jiffies + rose->t1;
- add_timer(&rose->timer);
+ sk_reset_timer(sk, &rose->timer, rose->timer.expires);
}
void rose_start_t2timer(struct sock *sk)
{
struct rose_sock *rose = rose_sk(sk);
- del_timer(&rose->timer);
+ sk_stop_timer(sk, &rose->timer);
rose->timer.function = rose_timer_expiry;
rose->timer.expires = jiffies + rose->t2;
- add_timer(&rose->timer);
+ sk_reset_timer(sk, &rose->timer, rose->timer.expires);
}
void rose_start_t3timer(struct sock *sk)
{
struct rose_sock *rose = rose_sk(sk);
- del_timer(&rose->timer);
+ sk_stop_timer(sk, &rose->timer);
rose->timer.function = rose_timer_expiry;
rose->timer.expires = jiffies + rose->t3;
- add_timer(&rose->timer);
+ sk_reset_timer(sk, &rose->timer, rose->timer.expires);
}
void rose_start_hbtimer(struct sock *sk)
{
struct rose_sock *rose = rose_sk(sk);
- del_timer(&rose->timer);
+ sk_stop_timer(sk, &rose->timer);
rose->timer.function = rose_timer_expiry;
rose->timer.expires = jiffies + rose->hb;
- add_timer(&rose->timer);
+ sk_reset_timer(sk, &rose->timer, rose->timer.expires);
}
void rose_start_idletimer(struct sock *sk)
{
struct rose_sock *rose = rose_sk(sk);
- del_timer(&rose->idletimer);
+ sk_stop_timer(sk, &rose->idletimer);
if (rose->idle > 0) {
rose->idletimer.function = rose_idletimer_expiry;
rose->idletimer.expires = jiffies + rose->idle;
- add_timer(&rose->idletimer);
+ sk_reset_timer(sk, &rose->idletimer, rose->idletimer.expires);
}
}
void rose_stop_heartbeat(struct sock *sk)
{
- del_timer(&sk->sk_timer);
+ sk_stop_timer(sk, &sk->sk_timer);
}
void rose_stop_timer(struct sock *sk)
{
- del_timer(&rose_sk(sk)->timer);
+ sk_stop_timer(sk, &rose_sk(sk)->timer);
}
void rose_stop_idletimer(struct sock *sk)
{
- del_timer(&rose_sk(sk)->idletimer);
+ sk_stop_timer(sk, &rose_sk(sk)->idletimer);
}
static void rose_heartbeat_expiry(struct timer_list *t)
@@ -133,6 +133,7 @@ static void rose_heartbeat_expiry(struct timer_list *t)
(sk->sk_state == TCP_LISTEN && sock_flag(sk, SOCK_DEAD))) {
bh_unlock_sock(sk);
rose_destroy_socket(sk);
+ sock_put(sk);
return;
}
break;
@@ -155,6 +156,7 @@ static void rose_heartbeat_expiry(struct timer_list *t)
rose_start_heartbeat(sk);
bh_unlock_sock(sk);
+ sock_put(sk);
}
static void rose_timer_expiry(struct timer_list *t)
@@ -184,6 +186,7 @@ static void rose_timer_expiry(struct timer_list *t)
break;
}
bh_unlock_sock(sk);
+ sock_put(sk);
}
static void rose_idletimer_expiry(struct timer_list *t)
@@ -208,4 +211,5 @@ static void rose_idletimer_expiry(struct timer_list *t)
sock_set_flag(sk, SOCK_DEAD);
}
bh_unlock_sock(sk);
+ sock_put(sk);
}
diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c
index fe190a691..5a01479aa 100644
--- a/net/rxrpc/local_object.c
+++ b/net/rxrpc/local_object.c
@@ -452,6 +452,9 @@ static void rxrpc_local_processor(struct work_struct *work)
container_of(work, struct rxrpc_local, processor);
bool again;
+ if (local->dead)
+ return;
+
trace_rxrpc_local(local->debug_id, rxrpc_local_processing,
atomic_read(&local->usage), NULL);
diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c
index 0256777b8..4c7fa1cfd 100644
--- a/net/sched/cls_route.c
+++ b/net/sched/cls_route.c
@@ -427,6 +427,11 @@ static int route4_set_parms(struct net *net, struct tcf_proto *tp,
return -EINVAL;
}
+ if (!nhandle) {
+ NL_SET_ERR_MSG(extack, "Replacing with handle of 0 is invalid");
+ return -EINVAL;
+ }
+
h1 = to_hash(nhandle);
b = rtnl_dereference(head->table[h1]);
if (!b) {
@@ -480,6 +485,11 @@ static int route4_change(struct net *net, struct sk_buff *in_skb,
int err;
bool new = true;
+ if (!handle) {
+ NL_SET_ERR_MSG(extack, "Creating with handle of 0 is invalid");
+ return -EINVAL;
+ }
+
if (opt == NULL)
return handle ? -EINVAL : 0;
@@ -528,7 +538,7 @@ static int route4_change(struct net *net, struct sk_buff *in_skb,
rcu_assign_pointer(f->next, f1);
rcu_assign_pointer(*fp, f);
- if (fold && fold->handle && f->handle != fold->handle) {
+ if (fold) {
th = to_hash(fold->handle);
h = from_hash(fold->handle >> 16);
b = rtnl_dereference(head->table[th]);
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 7c1b1eff8..c966dacf1 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -397,7 +397,7 @@ 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)) {
@@ -970,8 +970,6 @@ static void qdisc_destroy(struct Qdisc *qdisc)
const struct Qdisc_ops *ops;
struct sk_buff *skb, *tmp;
- if (!qdisc)
- return;
ops = qdisc->ops;
#ifdef CONFIG_NET_SCHED
@@ -1003,6 +1001,9 @@ static void qdisc_destroy(struct Qdisc *qdisc)
void qdisc_put(struct Qdisc *qdisc)
{
+ if (!qdisc)
+ return;
+
if (qdisc->flags & TCQ_F_BUILTIN ||
!refcount_dec_and_test(&qdisc->refcnt))
return;
diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index ad400f4f9..31793af1a 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -1120,9 +1120,9 @@ static int netem_dump(struct Qdisc *sch, struct sk_buff *skb)
struct tc_netem_rate rate;
struct tc_netem_slot slot;
- qopt.latency = min_t(psched_tdiff_t, PSCHED_NS2TICKS(q->latency),
+ qopt.latency = min_t(psched_time_t, PSCHED_NS2TICKS(q->latency),
UINT_MAX);
- qopt.jitter = min_t(psched_tdiff_t, PSCHED_NS2TICKS(q->jitter),
+ qopt.jitter = min_t(psched_time_t, PSCHED_NS2TICKS(q->jitter),
UINT_MAX);
qopt.limit = q->limit;
qopt.loss = q->loss;
diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c
index 81d205acb..a8ef8efa6 100644
--- a/net/sched/sch_sfb.c
+++ b/net/sched/sch_sfb.c
@@ -139,15 +139,15 @@ static void increment_one_qlen(u32 sfbhash, u32 slot, struct sfb_sched_data *q)
}
}
-static void increment_qlen(const struct sk_buff *skb, struct sfb_sched_data *q)
+static void increment_qlen(const struct sfb_skb_cb *cb, struct sfb_sched_data *q)
{
u32 sfbhash;
- sfbhash = sfb_hash(skb, 0);
+ sfbhash = cb->hashes[0];
if (sfbhash)
increment_one_qlen(sfbhash, 0, q);
- sfbhash = sfb_hash(skb, 1);
+ sfbhash = cb->hashes[1];
if (sfbhash)
increment_one_qlen(sfbhash, 1, q);
}
@@ -285,8 +285,10 @@ static int sfb_enqueue(struct sk_buff *skb, struct Qdisc *sch,
{
struct sfb_sched_data *q = qdisc_priv(sch);
+ unsigned int len = qdisc_pkt_len(skb);
struct Qdisc *child = q->qdisc;
struct tcf_proto *fl;
+ struct sfb_skb_cb cb;
int i;
u32 p_min = ~0;
u32 minqlen = ~0;
@@ -403,11 +405,12 @@ static int sfb_enqueue(struct sk_buff *skb, struct Qdisc *sch,
}
enqueue:
+ memcpy(&cb, sfb_skb_cb(skb), sizeof(cb));
ret = qdisc_enqueue(skb, child, to_free);
if (likely(ret == NET_XMIT_SUCCESS)) {
- qdisc_qstats_backlog_inc(sch, skb);
+ sch->qstats.backlog += len;
sch->q.qlen++;
- increment_qlen(skb, q);
+ increment_qlen(&cb, q);
} else if (net_xmit_drop_count(ret)) {
q->stats.childdrop++;
qdisc_qstats_drop(sch);
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index 7207a9769..8db8209c5 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -373,7 +373,7 @@ static int sctp_v4_available(union sctp_addr *addr, struct sctp_sock *sp)
if (addr->v4.sin_addr.s_addr != htonl(INADDR_ANY) &&
ret != RTN_LOCAL &&
!sp->inet.freebind &&
- !net->ipv4.sysctl_ip_nonlocal_bind)
+ !READ_ONCE(net->ipv4.sysctl_ip_nonlocal_bind))
return 0;
if (ipv6_only_sock(sctp_opt2sk(sp)))
diff --git a/net/sctp/stream_sched.c b/net/sctp/stream_sched.c
index a6c04a94b..3a5c0d00e 100644
--- a/net/sctp/stream_sched.c
+++ b/net/sctp/stream_sched.c
@@ -178,7 +178,7 @@ 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/smc/af_smc.c b/net/smc/af_smc.c
index 4c904ab29..dcd00b514 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -1031,7 +1031,6 @@ static void smc_listen_out_connected(struct smc_sock *new_smc)
{
struct sock *newsmcsk = &new_smc->sk;
- sk_refcnt_debug_inc(newsmcsk);
if (newsmcsk->sk_state == SMC_INIT)
newsmcsk->sk_state = SMC_ACTIVE;
diff --git a/net/socket.c b/net/socket.c
index e5cc9f2b9..a5167f03c 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -1619,7 +1619,7 @@ 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/sunrpc/backchannel_rqst.c b/net/sunrpc/backchannel_rqst.c
index 3c15a99b9..e41427e17 100644
--- a/net/sunrpc/backchannel_rqst.c
+++ b/net/sunrpc/backchannel_rqst.c
@@ -69,6 +69,17 @@ static void xprt_free_allocation(struct rpc_rqst *req)
kfree(req);
}
+static void xprt_bc_reinit_xdr_buf(struct xdr_buf *buf)
+{
+ buf->head[0].iov_len = PAGE_SIZE;
+ buf->tail[0].iov_len = 0;
+ buf->pages = NULL;
+ buf->page_len = 0;
+ buf->flags = 0;
+ buf->len = 0;
+ buf->buflen = PAGE_SIZE;
+}
+
static int xprt_alloc_xdr_buf(struct xdr_buf *buf, gfp_t gfp_flags)
{
struct page *page;
@@ -291,6 +302,9 @@ void xprt_free_bc_rqst(struct rpc_rqst *req)
*/
spin_lock_bh(&xprt->bc_pa_lock);
if (xprt_need_to_requeue(xprt)) {
+ xprt_bc_reinit_xdr_buf(&req->rq_snd_buf);
+ xprt_bc_reinit_xdr_buf(&req->rq_rcv_buf);
+ req->rq_rcv_buf.len = PAGE_SIZE;
list_add_tail(&req->rq_bc_pa_list, &xprt->bc_pa_list);
xprt->bc_alloc_count++;
req = NULL;
diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c
index 34596d0e4..7459180e9 100644
--- a/net/sunrpc/xdr.c
+++ b/net/sunrpc/xdr.c
@@ -544,7 +544,7 @@ static __be32 *xdr_get_next_encode_buffer(struct xdr_stream *xdr,
*/
xdr->p = (void *)p + frag2bytes;
space_left = xdr->buf->buflen - xdr->buf->len;
- if (space_left - nbytes >= PAGE_SIZE)
+ if (space_left - frag1bytes >= PAGE_SIZE)
xdr->end = (void *)p + PAGE_SIZE;
else
xdr->end = (void *)p + space_left - frag1bytes;
diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index d05fa7c36..b1abf4848 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -1550,9 +1550,9 @@ static void xprt_destroy(struct rpc_xprt *xprt)
* is cleared. We use ->transport_lock to ensure the mod_timer()
* can only run *before* del_time_sync(), never after.
*/
- spin_lock(&xprt->transport_lock);
+ spin_lock_bh(&xprt->transport_lock);
del_timer_sync(&xprt->timer);
- spin_unlock(&xprt->transport_lock);
+ spin_unlock_bh(&xprt->transport_lock);
/*
* Destroy sockets etc from the system workqueue so they can
diff --git a/net/tipc/monitor.c b/net/tipc/monitor.c
index 7b6c1c5c3..0268857a3 100644
--- a/net/tipc/monitor.c
+++ b/net/tipc/monitor.c
@@ -130,7 +130,7 @@ static void map_set(u64 *up_map, int i, unsigned int v)
static int map_get(u64 up_map, int i)
{
- return (up_map & (1 << i)) >> i;
+ return (up_map & (1ULL << i)) >> i;
}
static struct tipc_peer *peer_prev(struct tipc_peer *peer)
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 6c18b4565..8266452c1 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -453,6 +453,7 @@ static int tipc_sk_create(struct net *net, struct socket *sock,
sock_init_data(sock, sk);
tipc_set_sk_state(sk, TIPC_OPEN);
if (tipc_sk_insert(tsk)) {
+ sk_free(sk);
pr_warn("Socket create failed; port number exhausted\n");
return -EINVAL;
}
diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c
index 228e3ce48..b290eb3ae 100644
--- a/net/tls/tls_device.c
+++ b/net/tls/tls_device.c
@@ -110,13 +110,16 @@ static void tls_device_queue_ctx_destruction(struct tls_context *ctx)
unsigned long flags;
spin_lock_irqsave(&tls_device_lock, flags);
+ if (unlikely(!refcount_dec_and_test(&ctx->refcount)))
+ goto unlock;
+
list_move_tail(&ctx->list, &tls_device_gc_list);
/* schedule_work inside the spinlock
* to make sure tls_device_down waits for that work.
*/
schedule_work(&tls_device_gc_work);
-
+unlock:
spin_unlock_irqrestore(&tls_device_lock, flags);
}
@@ -214,8 +217,7 @@ void tls_device_sk_destruct(struct sock *sk)
clean_acked_data_disable(inet_csk(sk));
}
- if (refcount_dec_and_test(&tls_ctx->refcount))
- tls_device_queue_ctx_destruction(tls_ctx);
+ tls_device_queue_ctx_destruction(tls_ctx);
}
EXPORT_SYMBOL(tls_device_sk_destruct);
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index 22931a5f6..d55a47858 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -1118,6 +1118,7 @@ static void vsock_connect_timeout(struct work_struct *work)
if (sk->sk_state == TCP_SYN_SENT &&
(sk->sk_shutdown != SHUTDOWN_MASK)) {
sk->sk_state = TCP_CLOSE;
+ sk->sk_socket->state = SS_UNCONNECTED;
sk->sk_err = ETIMEDOUT;
sk->sk_error_report(sk);
vsock_transport_cancel_pkt(vsk);
@@ -1215,7 +1216,14 @@ static int vsock_stream_connect(struct socket *sock, struct sockaddr *addr,
* timeout fires.
*/
sock_hold(sk);
- schedule_delayed_work(&vsk->connect_work, timeout);
+
+ /* If the timeout function is already scheduled,
+ * reschedule it, then ungrab the socket refcount to
+ * keep it balanced.
+ */
+ if (mod_delayed_work(system_wq, &vsk->connect_work,
+ timeout))
+ sock_put(sk);
/* Skip ahead to preserve error code set above. */
goto out_wait;
diff --git a/net/wireless/debugfs.c b/net/wireless/debugfs.c
index 30fc6eb35..e6410487e 100644
--- a/net/wireless/debugfs.c
+++ b/net/wireless/debugfs.c
@@ -68,9 +68,10 @@ static ssize_t ht40allow_map_read(struct file *file,
{
struct wiphy *wiphy = file->private_data;
char *buf;
- unsigned int offset = 0, buf_size = PAGE_SIZE, i, r;
+ unsigned int offset = 0, buf_size = PAGE_SIZE, i;
enum nl80211_band band;
struct ieee80211_supported_band *sband;
+ ssize_t r;
buf = kzalloc(buf_size, GFP_KERNEL);
if (!buf)
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index bb1c94e20..1cd21a8c4 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -1697,8 +1697,10 @@ static int xfrm_expand_policies(const struct flowi *fl, u16 family,
*num_xfrms = 0;
return 0;
}
- if (IS_ERR(pols[0]))
+ if (IS_ERR(pols[0])) {
+ *num_pols = 0;
return PTR_ERR(pols[0]);
+ }
*num_xfrms = pols[0]->xfrm_nr;
@@ -1713,6 +1715,7 @@ static int xfrm_expand_policies(const struct flowi *fl, u16 family,
if (pols[1]) {
if (IS_ERR(pols[1])) {
xfrm_pols_put(pols, *num_pols);
+ *num_pols = 0;
return PTR_ERR(pols[1]);
}
(*num_pols)++;
@@ -2400,6 +2403,7 @@ 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();