summaryrefslogtreecommitdiffstats
path: root/net
diff options
context:
space:
mode:
authorDaniel Baumann <daniel.baumann@progress-linux.org>2024-05-07 02:18:06 +0000
committerDaniel Baumann <daniel.baumann@progress-linux.org>2024-05-07 02:18:06 +0000
commitdbbf0dcdfc9a5d90d5146bb195fce97064d92c76 (patch)
treebab1434b47a284ca2893dcc0b908d1b95d982e7c /net
parentAdding upstream version 6.1.85. (diff)
downloadlinux-dbbf0dcdfc9a5d90d5146bb195fce97064d92c76.tar.xz
linux-dbbf0dcdfc9a5d90d5146bb195fce97064d92c76.zip
Adding upstream version 6.1.90.upstream/6.1.90upstream
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to 'net')
-rw-r--r--net/ax25/af_ax25.c2
-rw-r--r--net/batman-adv/translation-table.c2
-rw-r--r--net/bluetooth/hci_request.c4
-rw-r--r--net/bluetooth/l2cap_sock.c59
-rw-r--r--net/bluetooth/mgmt.c24
-rw-r--r--net/bluetooth/sco.c30
-rw-r--r--net/bridge/br_input.c15
-rw-r--r--net/bridge/br_netfilter_hooks.c6
-rw-r--r--net/bridge/br_netlink.c2
-rw-r--r--net/bridge/br_private.h1
-rw-r--r--net/bridge/netfilter/nf_conntrack_bridge.c14
-rw-r--r--net/core/sock.c1
-rw-r--r--net/core/sysctl_net_core.c9
-rw-r--r--net/dsa/dsa2.c24
-rw-r--r--net/ethernet/eth.c12
-rw-r--r--net/ipv4/icmp.c12
-rw-r--r--net/ipv4/netfilter/arp_tables.c4
-rw-r--r--net/ipv4/netfilter/ip_tables.c4
-rw-r--r--net/ipv4/route.c7
-rw-r--r--net/ipv4/udp.c5
-rw-r--r--net/ipv6/addrconf.c7
-rw-r--r--net/ipv6/ip6_fib.c7
-rw-r--r--net/ipv6/netfilter/ip6_tables.c4
-rw-r--r--net/ipv6/udp.c5
-rw-r--r--net/mpls/mpls_gso.c3
-rw-r--r--net/netfilter/ipvs/ip_vs_proto_sctp.c6
-rw-r--r--net/netfilter/nf_flow_table_inet.c3
-rw-r--r--net/netfilter/nf_flow_table_ip.c10
-rw-r--r--net/netfilter/nf_tables_api.c63
-rw-r--r--net/netfilter/nft_chain_filter.c4
-rw-r--r--net/netfilter/nft_set_pipapo.c14
-rw-r--r--net/openvswitch/conntrack.c9
-rw-r--r--net/smc/smc_pnet.c10
-rw-r--r--net/unix/af_unix.c20
-rw-r--r--net/unix/garbage.c35
-rw-r--r--net/unix/scm.c8
-rw-r--r--net/xdp/xsk.c2
37 files changed, 297 insertions, 150 deletions
diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index 6b4c25a92..0bffac238 100644
--- a/net/ax25/af_ax25.c
+++ b/net/ax25/af_ax25.c
@@ -103,7 +103,7 @@ again:
s->ax25_dev = NULL;
if (sk->sk_socket) {
netdev_put(ax25_dev->dev,
- &ax25_dev->dev_tracker);
+ &s->dev_tracker);
ax25_dev_put(ax25_dev);
}
ax25_cb_del(s);
diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c
index 5d8cee747..4fc66cd95 100644
--- a/net/batman-adv/translation-table.c
+++ b/net/batman-adv/translation-table.c
@@ -3948,7 +3948,7 @@ void batadv_tt_local_resize_to_mtu(struct net_device *soft_iface)
spin_lock_bh(&bat_priv->tt.commit_lock);
- while (true) {
+ while (timeout) {
table_size = batadv_tt_local_table_transmit_size(bat_priv);
if (packet_size_max >= table_size)
break;
diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c
index 4468647df..cf69e973b 100644
--- a/net/bluetooth/hci_request.c
+++ b/net/bluetooth/hci_request.c
@@ -105,8 +105,10 @@ void hci_req_sync_complete(struct hci_dev *hdev, u8 result, u16 opcode,
if (hdev->req_status == HCI_REQ_PEND) {
hdev->req_result = result;
hdev->req_status = HCI_REQ_DONE;
- if (skb)
+ if (skb) {
+ kfree_skb(hdev->req_skb);
hdev->req_skb = skb_get(skb);
+ }
wake_up_interruptible(&hdev->req_wait_q);
}
}
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index 947ca580b..e3c7029ec 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -457,7 +457,8 @@ static int l2cap_sock_getsockopt_old(struct socket *sock, int optname,
struct l2cap_chan *chan = l2cap_pi(sk)->chan;
struct l2cap_options opts;
struct l2cap_conninfo cinfo;
- int len, err = 0;
+ int err = 0;
+ size_t len;
u32 opt;
BT_DBG("sk %p", sk);
@@ -504,7 +505,7 @@ static int l2cap_sock_getsockopt_old(struct socket *sock, int optname,
BT_DBG("mode 0x%2.2x", chan->mode);
- len = min_t(unsigned int, len, sizeof(opts));
+ len = min(len, sizeof(opts));
if (copy_to_user(optval, (char *) &opts, len))
err = -EFAULT;
@@ -554,7 +555,7 @@ static int l2cap_sock_getsockopt_old(struct socket *sock, int optname,
cinfo.hci_handle = chan->conn->hcon->handle;
memcpy(cinfo.dev_class, chan->conn->hcon->dev_class, 3);
- len = min_t(unsigned int, len, sizeof(cinfo));
+ len = min(len, sizeof(cinfo));
if (copy_to_user(optval, (char *) &cinfo, len))
err = -EFAULT;
@@ -745,7 +746,7 @@ static int l2cap_sock_setsockopt_old(struct socket *sock, int optname,
struct sock *sk = sock->sk;
struct l2cap_chan *chan = l2cap_pi(sk)->chan;
struct l2cap_options opts;
- int len, err = 0;
+ int err = 0;
u32 opt;
BT_DBG("sk %p", sk);
@@ -772,11 +773,9 @@ static int l2cap_sock_setsockopt_old(struct socket *sock, int optname,
opts.max_tx = chan->max_tx;
opts.txwin_size = chan->tx_win;
- len = min_t(unsigned int, sizeof(opts), optlen);
- if (copy_from_sockptr(&opts, optval, len)) {
- err = -EFAULT;
+ err = bt_copy_from_sockptr(&opts, sizeof(opts), optval, optlen);
+ if (err)
break;
- }
if (opts.txwin_size > L2CAP_DEFAULT_EXT_WINDOW) {
err = -EINVAL;
@@ -819,10 +818,9 @@ static int l2cap_sock_setsockopt_old(struct socket *sock, int optname,
break;
case L2CAP_LM:
- if (copy_from_sockptr(&opt, optval, sizeof(u32))) {
- err = -EFAULT;
+ err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen);
+ if (err)
break;
- }
if (opt & L2CAP_LM_FIPS) {
err = -EINVAL;
@@ -903,7 +901,7 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname,
struct bt_security sec;
struct bt_power pwr;
struct l2cap_conn *conn;
- int len, err = 0;
+ int err = 0;
u32 opt;
u16 mtu;
u8 mode;
@@ -929,11 +927,9 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname,
sec.level = BT_SECURITY_LOW;
- len = min_t(unsigned int, sizeof(sec), optlen);
- if (copy_from_sockptr(&sec, optval, len)) {
- err = -EFAULT;
+ err = bt_copy_from_sockptr(&sec, sizeof(sec), optval, optlen);
+ if (err)
break;
- }
if (sec.level < BT_SECURITY_LOW ||
sec.level > BT_SECURITY_FIPS) {
@@ -978,10 +974,9 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname,
break;
}
- if (copy_from_sockptr(&opt, optval, sizeof(u32))) {
- err = -EFAULT;
+ err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen);
+ if (err)
break;
- }
if (opt) {
set_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags);
@@ -993,10 +988,9 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname,
break;
case BT_FLUSHABLE:
- if (copy_from_sockptr(&opt, optval, sizeof(u32))) {
- err = -EFAULT;
+ err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen);
+ if (err)
break;
- }
if (opt > BT_FLUSHABLE_ON) {
err = -EINVAL;
@@ -1028,11 +1022,9 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname,
pwr.force_active = BT_POWER_FORCE_ACTIVE_ON;
- len = min_t(unsigned int, sizeof(pwr), optlen);
- if (copy_from_sockptr(&pwr, optval, len)) {
- err = -EFAULT;
+ err = bt_copy_from_sockptr(&pwr, sizeof(pwr), optval, optlen);
+ if (err)
break;
- }
if (pwr.force_active)
set_bit(FLAG_FORCE_ACTIVE, &chan->flags);
@@ -1041,10 +1033,9 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname,
break;
case BT_CHANNEL_POLICY:
- if (copy_from_sockptr(&opt, optval, sizeof(u32))) {
- err = -EFAULT;
+ err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen);
+ if (err)
break;
- }
if (opt > BT_CHANNEL_POLICY_AMP_PREFERRED) {
err = -EINVAL;
@@ -1089,10 +1080,9 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname,
break;
}
- if (copy_from_sockptr(&mtu, optval, sizeof(u16))) {
- err = -EFAULT;
+ err = bt_copy_from_sockptr(&mtu, sizeof(mtu), optval, optlen);
+ if (err)
break;
- }
if (chan->mode == L2CAP_MODE_EXT_FLOWCTL &&
sk->sk_state == BT_CONNECTED)
@@ -1120,10 +1110,9 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname,
break;
}
- if (copy_from_sockptr(&mode, optval, sizeof(u8))) {
- err = -EFAULT;
+ err = bt_copy_from_sockptr(&mode, sizeof(mode), optval, optlen);
+ if (err)
break;
- }
BT_DBG("mode %u", mode);
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 716f6dc49..76dac5a90 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -2680,7 +2680,11 @@ static int add_uuid(struct sock *sk, struct hci_dev *hdev, void *data, u16 len)
goto failed;
}
- err = hci_cmd_sync_queue(hdev, add_uuid_sync, cmd, mgmt_class_complete);
+ /* MGMT_OP_ADD_UUID don't require adapter the UP/Running so use
+ * hci_cmd_sync_submit instead of hci_cmd_sync_queue.
+ */
+ err = hci_cmd_sync_submit(hdev, add_uuid_sync, cmd,
+ mgmt_class_complete);
if (err < 0) {
mgmt_pending_free(cmd);
goto failed;
@@ -2774,8 +2778,11 @@ update_class:
goto unlock;
}
- err = hci_cmd_sync_queue(hdev, remove_uuid_sync, cmd,
- mgmt_class_complete);
+ /* MGMT_OP_REMOVE_UUID don't require adapter the UP/Running so use
+ * hci_cmd_sync_submit instead of hci_cmd_sync_queue.
+ */
+ err = hci_cmd_sync_submit(hdev, remove_uuid_sync, cmd,
+ mgmt_class_complete);
if (err < 0)
mgmt_pending_free(cmd);
@@ -2841,8 +2848,11 @@ static int set_dev_class(struct sock *sk, struct hci_dev *hdev, void *data,
goto unlock;
}
- err = hci_cmd_sync_queue(hdev, set_class_sync, cmd,
- mgmt_class_complete);
+ /* MGMT_OP_SET_DEV_CLASS don't require adapter the UP/Running so use
+ * hci_cmd_sync_submit instead of hci_cmd_sync_queue.
+ */
+ err = hci_cmd_sync_submit(hdev, set_class_sync, cmd,
+ mgmt_class_complete);
if (err < 0)
mgmt_pending_free(cmd);
@@ -5530,8 +5540,8 @@ static int remove_adv_monitor(struct sock *sk, struct hci_dev *hdev,
goto unlock;
}
- err = hci_cmd_sync_queue(hdev, mgmt_remove_adv_monitor_sync, cmd,
- mgmt_remove_adv_monitor_complete);
+ err = hci_cmd_sync_submit(hdev, mgmt_remove_adv_monitor_sync, cmd,
+ mgmt_remove_adv_monitor_complete);
if (err) {
mgmt_pending_remove(cmd);
diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c
index 6d4168cfe..4a6bf60f3 100644
--- a/net/bluetooth/sco.c
+++ b/net/bluetooth/sco.c
@@ -831,7 +831,7 @@ static int sco_sock_setsockopt(struct socket *sock, int level, int optname,
sockptr_t optval, unsigned int optlen)
{
struct sock *sk = sock->sk;
- int len, err = 0;
+ int err = 0;
struct bt_voice voice;
u32 opt;
struct bt_codecs *codecs;
@@ -850,10 +850,9 @@ static int sco_sock_setsockopt(struct socket *sock, int level, int optname,
break;
}
- if (copy_from_sockptr(&opt, optval, sizeof(u32))) {
- err = -EFAULT;
+ err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen);
+ if (err)
break;
- }
if (opt)
set_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags);
@@ -870,11 +869,10 @@ static int sco_sock_setsockopt(struct socket *sock, int level, int optname,
voice.setting = sco_pi(sk)->setting;
- len = min_t(unsigned int, sizeof(voice), optlen);
- if (copy_from_sockptr(&voice, optval, len)) {
- err = -EFAULT;
+ err = bt_copy_from_sockptr(&voice, sizeof(voice), optval,
+ optlen);
+ if (err)
break;
- }
/* Explicitly check for these values */
if (voice.setting != BT_VOICE_TRANSPARENT &&
@@ -897,10 +895,9 @@ static int sco_sock_setsockopt(struct socket *sock, int level, int optname,
break;
case BT_PKT_STATUS:
- if (copy_from_sockptr(&opt, optval, sizeof(u32))) {
- err = -EFAULT;
+ err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen);
+ if (err)
break;
- }
if (opt)
sco_pi(sk)->cmsg_mask |= SCO_CMSG_PKT_STATUS;
@@ -941,9 +938,9 @@ static int sco_sock_setsockopt(struct socket *sock, int level, int optname,
break;
}
- if (copy_from_sockptr(buffer, optval, optlen)) {
+ err = bt_copy_from_sockptr(buffer, optlen, optval, optlen);
+ if (err) {
hci_dev_put(hdev);
- err = -EFAULT;
break;
}
@@ -974,7 +971,8 @@ static int sco_sock_getsockopt_old(struct socket *sock, int optname,
struct sock *sk = sock->sk;
struct sco_options opts;
struct sco_conninfo cinfo;
- int len, err = 0;
+ int err = 0;
+ size_t len;
BT_DBG("sk %p", sk);
@@ -996,7 +994,7 @@ static int sco_sock_getsockopt_old(struct socket *sock, int optname,
BT_DBG("mtu %u", opts.mtu);
- len = min_t(unsigned int, len, sizeof(opts));
+ len = min(len, sizeof(opts));
if (copy_to_user(optval, (char *)&opts, len))
err = -EFAULT;
@@ -1014,7 +1012,7 @@ static int sco_sock_getsockopt_old(struct socket *sock, int optname,
cinfo.hci_handle = sco_pi(sk)->conn->hcon->handle;
memcpy(cinfo.dev_class, sco_pi(sk)->conn->hcon->dev_class, 3);
- len = min_t(unsigned int, len, sizeof(cinfo));
+ len = min(len, sizeof(cinfo));
if (copy_to_user(optval, (char *)&cinfo, len))
err = -EFAULT;
diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c
index 6bb272894..b94a17839 100644
--- a/net/bridge/br_input.c
+++ b/net/bridge/br_input.c
@@ -30,7 +30,7 @@ br_netif_receive_skb(struct net *net, struct sock *sk, struct sk_buff *skb)
return netif_receive_skb(skb);
}
-static int br_pass_frame_up(struct sk_buff *skb)
+static int br_pass_frame_up(struct sk_buff *skb, bool promisc)
{
struct net_device *indev, *brdev = BR_INPUT_SKB_CB(skb)->brdev;
struct net_bridge *br = netdev_priv(brdev);
@@ -65,6 +65,8 @@ static int br_pass_frame_up(struct sk_buff *skb)
br_multicast_count(br, NULL, skb, br_multicast_igmp_type(skb),
BR_MCAST_DIR_TX);
+ BR_INPUT_SKB_CB(skb)->promisc = promisc;
+
return NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_IN,
dev_net(indev), NULL, skb, indev, NULL,
br_netif_receive_skb);
@@ -82,6 +84,7 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb
struct net_bridge_mcast *brmctx;
struct net_bridge_vlan *vlan;
struct net_bridge *br;
+ bool promisc;
u16 vid = 0;
u8 state;
@@ -120,7 +123,9 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb
if (p->flags & BR_LEARNING)
br_fdb_update(br, p, eth_hdr(skb)->h_source, vid, 0);
- local_rcv = !!(br->dev->flags & IFF_PROMISC);
+ promisc = !!(br->dev->flags & IFF_PROMISC);
+ local_rcv = promisc;
+
if (is_multicast_ether_addr(eth_hdr(skb)->h_dest)) {
/* by definition the broadcast is also a multicast address */
if (is_broadcast_ether_addr(eth_hdr(skb)->h_dest)) {
@@ -183,7 +188,7 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb
unsigned long now = jiffies;
if (test_bit(BR_FDB_LOCAL, &dst->flags))
- return br_pass_frame_up(skb);
+ return br_pass_frame_up(skb, false);
if (now != dst->used)
dst->used = now;
@@ -196,7 +201,7 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb
}
if (local_rcv)
- return br_pass_frame_up(skb);
+ return br_pass_frame_up(skb, promisc);
out:
return 0;
@@ -368,6 +373,8 @@ static rx_handler_result_t br_handle_frame(struct sk_buff **pskb)
goto forward;
}
+ BR_INPUT_SKB_CB(skb)->promisc = false;
+
/* The else clause should be hit when nf_hook():
* - returns < 0 (drop/error)
* - returns = 0 (stolen/nf_queue)
diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c
index bff48d576..9ac70c27d 100644
--- a/net/bridge/br_netfilter_hooks.c
+++ b/net/bridge/br_netfilter_hooks.c
@@ -600,11 +600,17 @@ static unsigned int br_nf_local_in(void *priv,
struct sk_buff *skb,
const struct nf_hook_state *state)
{
+ bool promisc = BR_INPUT_SKB_CB(skb)->promisc;
struct nf_conntrack *nfct = skb_nfct(skb);
const struct nf_ct_hook *ct_hook;
struct nf_conn *ct;
int ret;
+ if (promisc) {
+ nf_reset_ct(skb);
+ return NF_ACCEPT;
+ }
+
if (!nfct || skb->pkt_type == PACKET_HOST)
return NF_ACCEPT;
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index d087fd4c7..d38eff277 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -650,7 +650,7 @@ void br_ifinfo_notify(int event, const struct net_bridge *br,
{
u32 filter = RTEXT_FILTER_BRVLAN_COMPRESSED;
- return br_info_notify(event, br, port, filter);
+ br_info_notify(event, br, port, filter);
}
/*
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index 51d010f64..940de9516 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -559,6 +559,7 @@ struct br_input_skb_cb {
#endif
u8 proxyarp_replied:1;
u8 src_port_isolated:1;
+ u8 promisc:1;
#ifdef CONFIG_BRIDGE_VLAN_FILTERING
u8 vlan_filtered:1;
#endif
diff --git a/net/bridge/netfilter/nf_conntrack_bridge.c b/net/bridge/netfilter/nf_conntrack_bridge.c
index c7c27ada6..e60c38670 100644
--- a/net/bridge/netfilter/nf_conntrack_bridge.c
+++ b/net/bridge/netfilter/nf_conntrack_bridge.c
@@ -294,18 +294,24 @@ static unsigned int nf_ct_bridge_pre(void *priv, struct sk_buff *skb,
static unsigned int nf_ct_bridge_in(void *priv, struct sk_buff *skb,
const struct nf_hook_state *state)
{
- enum ip_conntrack_info ctinfo;
+ bool promisc = BR_INPUT_SKB_CB(skb)->promisc;
+ struct nf_conntrack *nfct = skb_nfct(skb);
struct nf_conn *ct;
- if (skb->pkt_type == PACKET_HOST)
+ if (promisc) {
+ nf_reset_ct(skb);
+ return NF_ACCEPT;
+ }
+
+ if (!nfct || skb->pkt_type == PACKET_HOST)
return NF_ACCEPT;
/* nf_conntrack_confirm() cannot handle concurrent clones,
* this happens for broad/multicast frames with e.g. macvlan on top
* of the bridge device.
*/
- ct = nf_ct_get(skb, &ctinfo);
- if (!ct || nf_ct_is_confirmed(ct) || nf_ct_is_template(ct))
+ ct = container_of(nfct, struct nf_conn, ct_general);
+ if (nf_ct_is_confirmed(ct) || nf_ct_is_template(ct))
return NF_ACCEPT;
/* let inet prerouting call conntrack again */
diff --git a/net/core/sock.c b/net/core/sock.c
index c8803b95e..550af616f 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -279,6 +279,7 @@ __u32 sysctl_rmem_max __read_mostly = SK_RMEM_MAX;
EXPORT_SYMBOL(sysctl_rmem_max);
__u32 sysctl_wmem_default __read_mostly = SK_WMEM_MAX;
__u32 sysctl_rmem_default __read_mostly = SK_RMEM_MAX;
+int sysctl_mem_pcpu_rsv __read_mostly = SK_MEMORY_PCPU_RESERVE;
/* Maximal space eaten by iovec or ancillary data plus some space */
int sysctl_optmem_max __read_mostly = sizeof(unsigned long)*(2*UIO_MAXIOV+512);
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index 5b1ce656b..d281d5343 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -29,6 +29,7 @@ static int int_3600 = 3600;
static int min_sndbuf = SOCK_MIN_SNDBUF;
static int min_rcvbuf = SOCK_MIN_RCVBUF;
static int max_skb_frags = MAX_SKB_FRAGS;
+static int min_mem_pcpu_rsv = SK_MEMORY_PCPU_RESERVE;
static int net_msg_warn; /* Unused, but still a sysctl */
@@ -349,6 +350,14 @@ static struct ctl_table net_core_table[] = {
.extra1 = &min_rcvbuf,
},
{
+ .procname = "mem_pcpu_rsv",
+ .data = &sysctl_mem_pcpu_rsv,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &min_mem_pcpu_rsv,
+ },
+ {
.procname = "dev_weight",
.data = &weight_p,
.maxlen = sizeof(int),
diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c
index 5417f7b11..98f864879 100644
--- a/net/dsa/dsa2.c
+++ b/net/dsa/dsa2.c
@@ -425,6 +425,24 @@ static int dsa_tree_setup_default_cpu(struct dsa_switch_tree *dst)
return 0;
}
+static struct dsa_port *
+dsa_switch_preferred_default_local_cpu_port(struct dsa_switch *ds)
+{
+ struct dsa_port *cpu_dp;
+
+ if (!ds->ops->preferred_default_local_cpu_port)
+ return NULL;
+
+ cpu_dp = ds->ops->preferred_default_local_cpu_port(ds);
+ if (!cpu_dp)
+ return NULL;
+
+ if (WARN_ON(!dsa_port_is_cpu(cpu_dp) || cpu_dp->ds != ds))
+ return NULL;
+
+ return cpu_dp;
+}
+
/* Perform initial assignment of CPU ports to user ports and DSA links in the
* fabric, giving preference to CPU ports local to each switch. Default to
* using the first CPU port in the switch tree if the port does not have a CPU
@@ -432,12 +450,16 @@ static int dsa_tree_setup_default_cpu(struct dsa_switch_tree *dst)
*/
static int dsa_tree_setup_cpu_ports(struct dsa_switch_tree *dst)
{
- struct dsa_port *cpu_dp, *dp;
+ struct dsa_port *preferred_cpu_dp, *cpu_dp, *dp;
list_for_each_entry(cpu_dp, &dst->ports, list) {
if (!dsa_port_is_cpu(cpu_dp))
continue;
+ preferred_cpu_dp = dsa_switch_preferred_default_local_cpu_port(cpu_dp->ds);
+ if (preferred_cpu_dp && preferred_cpu_dp != cpu_dp)
+ continue;
+
/* Prefer a local CPU port */
dsa_switch_for_each_port(dp, cpu_dp->ds) {
/* Prefer the first local CPU port found */
diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c
index e02daa74e..5ba7b460c 100644
--- a/net/ethernet/eth.c
+++ b/net/ethernet/eth.c
@@ -164,17 +164,7 @@ __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev)
eth = (struct ethhdr *)skb->data;
skb_pull_inline(skb, ETH_HLEN);
- if (unlikely(!ether_addr_equal_64bits(eth->h_dest,
- dev->dev_addr))) {
- if (unlikely(is_multicast_ether_addr_64bits(eth->h_dest))) {
- if (ether_addr_equal_64bits(eth->h_dest, dev->broadcast))
- skb->pkt_type = PACKET_BROADCAST;
- else
- skb->pkt_type = PACKET_MULTICAST;
- } else {
- skb->pkt_type = PACKET_OTHERHOST;
- }
- }
+ eth_skb_pkt_type(skb, dev);
/*
* Some variants of DSA tagging don't have an ethertype field
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 2b09ef707..31051b327 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -92,6 +92,7 @@
#include <net/inet_common.h>
#include <net/ip_fib.h>
#include <net/l3mdev.h>
+#include <net/addrconf.h>
/*
* Build xmit assembly blocks
@@ -1029,6 +1030,8 @@ bool icmp_build_probe(struct sk_buff *skb, struct icmphdr *icmphdr)
struct icmp_ext_hdr *ext_hdr, _ext_hdr;
struct icmp_ext_echo_iio *iio, _iio;
struct net *net = dev_net(skb->dev);
+ struct inet6_dev *in6_dev;
+ struct in_device *in_dev;
struct net_device *dev;
char buff[IFNAMSIZ];
u16 ident_len;
@@ -1112,10 +1115,15 @@ bool icmp_build_probe(struct sk_buff *skb, struct icmphdr *icmphdr)
/* Fill bits in reply message */
if (dev->flags & IFF_UP)
status |= ICMP_EXT_ECHOREPLY_ACTIVE;
- if (__in_dev_get_rcu(dev) && __in_dev_get_rcu(dev)->ifa_list)
+
+ in_dev = __in_dev_get_rcu(dev);
+ if (in_dev && rcu_access_pointer(in_dev->ifa_list))
status |= ICMP_EXT_ECHOREPLY_IPV4;
- if (!list_empty(&rcu_dereference(dev->ip6_ptr)->addr_list))
+
+ in6_dev = __in6_dev_get(dev);
+ if (in6_dev && !list_empty(&in6_dev->addr_list))
status |= ICMP_EXT_ECHOREPLY_IPV6;
+
dev_put(dev);
icmphdr->un.echo.sequence |= htons(status);
return true;
diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index b150c9929..14365b20f 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -966,6 +966,8 @@ static int do_replace(struct net *net, sockptr_t arg, unsigned int len)
return -ENOMEM;
if (tmp.num_counters == 0)
return -EINVAL;
+ if ((u64)len < (u64)tmp.size + sizeof(tmp))
+ return -EINVAL;
tmp.name[sizeof(tmp.name)-1] = 0;
@@ -1266,6 +1268,8 @@ static int compat_do_replace(struct net *net, sockptr_t arg, unsigned int len)
return -ENOMEM;
if (tmp.num_counters == 0)
return -EINVAL;
+ if ((u64)len < (u64)tmp.size + sizeof(tmp))
+ return -EINVAL;
tmp.name[sizeof(tmp.name)-1] = 0;
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index 1f365e28e..a6208efcf 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -1120,6 +1120,8 @@ do_replace(struct net *net, sockptr_t arg, unsigned int len)
return -ENOMEM;
if (tmp.num_counters == 0)
return -EINVAL;
+ if ((u64)len < (u64)tmp.size + sizeof(tmp))
+ return -EINVAL;
tmp.name[sizeof(tmp.name)-1] = 0;
@@ -1506,6 +1508,8 @@ compat_do_replace(struct net *net, sockptr_t arg, unsigned int len)
return -ENOMEM;
if (tmp.num_counters == 0)
return -EINVAL;
+ if ((u64)len < (u64)tmp.size + sizeof(tmp))
+ return -EINVAL;
tmp.name[sizeof(tmp.name)-1] = 0;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 474f391fa..6c0f1e347 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -926,13 +926,11 @@ void ip_rt_send_redirect(struct sk_buff *skb)
icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, gw);
peer->rate_last = jiffies;
++peer->n_redirects;
-#ifdef CONFIG_IP_ROUTE_VERBOSE
- if (log_martians &&
+ if (IS_ENABLED(CONFIG_IP_ROUTE_VERBOSE) && log_martians &&
peer->n_redirects == ip_rt_redirect_number)
net_warn_ratelimited("host %pI4/if%d ignores redirects for %pI4 to %pI4\n",
&ip_hdr(skb)->saddr, inet_iif(skb),
&ip_hdr(skb)->daddr, &gw);
-#endif
}
out_put_peer:
inet_putpeer(peer);
@@ -2170,6 +2168,9 @@ int ip_route_use_hint(struct sk_buff *skb, __be32 daddr, __be32 saddr,
int err = -EINVAL;
u32 tag = 0;
+ if (!in_dev)
+ return -EINVAL;
+
if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr))
goto martian_source;
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 2a78c7818..39fae7581 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1141,16 +1141,17 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
if (msg->msg_controllen) {
err = udp_cmsg_send(sk, msg, &ipc.gso_size);
- if (err > 0)
+ if (err > 0) {
err = ip_cmsg_send(sk, msg, &ipc,
sk->sk_family == AF_INET6);
+ connected = 0;
+ }
if (unlikely(err < 0)) {
kfree(ipc.opt);
return err;
}
if (ipc.opt)
free = 1;
- connected = 0;
}
if (!ipc.opt) {
struct ip_options_rcu *inet_opt;
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 164837369..3866deaad 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -2050,9 +2050,10 @@ struct inet6_ifaddr *ipv6_get_ifaddr(struct net *net, const struct in6_addr *add
if (ipv6_addr_equal(&ifp->addr, addr)) {
if (!dev || ifp->idev->dev == dev ||
!(ifp->scope&(IFA_LINK|IFA_HOST) || strict)) {
- result = ifp;
- in6_ifa_hold(ifp);
- break;
+ if (in6_ifa_hold_safe(ifp)) {
+ result = ifp;
+ break;
+ }
}
}
}
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index e60637485..821362643 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -1376,7 +1376,10 @@ int fib6_add(struct fib6_node *root, struct fib6_info *rt,
struct nl_info *info, struct netlink_ext_ack *extack)
{
struct fib6_table *table = rt->fib6_table;
- struct fib6_node *fn, *pn = NULL;
+ struct fib6_node *fn;
+#ifdef CONFIG_IPV6_SUBTREES
+ struct fib6_node *pn = NULL;
+#endif
int err = -ENOMEM;
int allow_create = 1;
int replace_required = 0;
@@ -1400,9 +1403,9 @@ int fib6_add(struct fib6_node *root, struct fib6_info *rt,
goto out;
}
+#ifdef CONFIG_IPV6_SUBTREES
pn = fn;
-#ifdef CONFIG_IPV6_SUBTREES
if (rt->fib6_src.plen) {
struct fib6_node *sn;
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index 37a2b3301..b844e519d 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -1137,6 +1137,8 @@ do_replace(struct net *net, sockptr_t arg, unsigned int len)
return -ENOMEM;
if (tmp.num_counters == 0)
return -EINVAL;
+ if ((u64)len < (u64)tmp.size + sizeof(tmp))
+ return -EINVAL;
tmp.name[sizeof(tmp.name)-1] = 0;
@@ -1515,6 +1517,8 @@ compat_do_replace(struct net *net, sockptr_t arg, unsigned int len)
return -ENOMEM;
if (tmp.num_counters == 0)
return -EINVAL;
+ if ((u64)len < (u64)tmp.size + sizeof(tmp))
+ return -EINVAL;
tmp.name[sizeof(tmp.name)-1] = 0;
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 1775e9b9b..504ea27d0 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1493,9 +1493,11 @@ do_udp_sendmsg:
ipc6.opt = opt;
err = udp_cmsg_send(sk, msg, &ipc6.gso_size);
- if (err > 0)
+ if (err > 0) {
err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, fl6,
&ipc6);
+ connected = false;
+ }
if (err < 0) {
fl6_sock_release(flowlabel);
return err;
@@ -1507,7 +1509,6 @@ do_udp_sendmsg:
}
if (!(opt->opt_nflen|opt->opt_flen))
opt = NULL;
- connected = false;
}
if (!opt) {
opt = txopt_get(np);
diff --git a/net/mpls/mpls_gso.c b/net/mpls/mpls_gso.c
index 1482259de..40334d4d8 100644
--- a/net/mpls/mpls_gso.c
+++ b/net/mpls/mpls_gso.c
@@ -26,6 +26,9 @@ static struct sk_buff *mpls_gso_segment(struct sk_buff *skb,
__be16 mpls_protocol;
unsigned int mpls_hlen;
+ if (!skb_inner_network_header_was_set(skb))
+ goto out;
+
skb_reset_network_header(skb);
mpls_hlen = skb_inner_network_header(skb) - skb_network_header(skb);
if (unlikely(!mpls_hlen || mpls_hlen % MPLS_HLEN))
diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c
index a0921adc3..1e689c714 100644
--- a/net/netfilter/ipvs/ip_vs_proto_sctp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c
@@ -126,7 +126,8 @@ sctp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp,
if (sctph->source != cp->vport || payload_csum ||
skb->ip_summed == CHECKSUM_PARTIAL) {
sctph->source = cp->vport;
- sctp_nat_csum(skb, sctph, sctphoff);
+ if (!skb_is_gso(skb) || !skb_is_gso_sctp(skb))
+ sctp_nat_csum(skb, sctph, sctphoff);
} else {
skb->ip_summed = CHECKSUM_UNNECESSARY;
}
@@ -174,7 +175,8 @@ sctp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp,
(skb->ip_summed == CHECKSUM_PARTIAL &&
!(skb_dst(skb)->dev->features & NETIF_F_SCTP_CRC))) {
sctph->dest = cp->dport;
- sctp_nat_csum(skb, sctph, sctphoff);
+ if (!skb_is_gso(skb) || !skb_is_gso_sctp(skb))
+ sctp_nat_csum(skb, sctph, sctphoff);
} else if (skb->ip_summed != CHECKSUM_PARTIAL) {
skb->ip_summed = CHECKSUM_UNNECESSARY;
}
diff --git a/net/netfilter/nf_flow_table_inet.c b/net/netfilter/nf_flow_table_inet.c
index 9505f9d18..6eef15648 100644
--- a/net/netfilter/nf_flow_table_inet.c
+++ b/net/netfilter/nf_flow_table_inet.c
@@ -21,7 +21,8 @@ nf_flow_offload_inet_hook(void *priv, struct sk_buff *skb,
proto = veth->h_vlan_encapsulated_proto;
break;
case htons(ETH_P_PPP_SES):
- proto = nf_flow_pppoe_proto(skb);
+ if (!nf_flow_pppoe_proto(skb, &proto))
+ return NF_ACCEPT;
break;
default:
proto = skb->protocol;
diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c
index 6feaac9ab..22bc0e3d8 100644
--- a/net/netfilter/nf_flow_table_ip.c
+++ b/net/netfilter/nf_flow_table_ip.c
@@ -156,7 +156,7 @@ static void nf_flow_tuple_encap(struct sk_buff *skb,
tuple->encap[i].proto = skb->protocol;
break;
case htons(ETH_P_PPP_SES):
- phdr = (struct pppoe_hdr *)skb_mac_header(skb);
+ phdr = (struct pppoe_hdr *)skb_network_header(skb);
tuple->encap[i].id = ntohs(phdr->sid);
tuple->encap[i].proto = skb->protocol;
break;
@@ -267,10 +267,11 @@ static unsigned int nf_flow_xmit_xfrm(struct sk_buff *skb,
return NF_STOLEN;
}
-static bool nf_flow_skb_encap_protocol(const struct sk_buff *skb, __be16 proto,
+static bool nf_flow_skb_encap_protocol(struct sk_buff *skb, __be16 proto,
u32 *offset)
{
struct vlan_ethhdr *veth;
+ __be16 inner_proto;
switch (skb->protocol) {
case htons(ETH_P_8021Q):
@@ -281,7 +282,8 @@ static bool nf_flow_skb_encap_protocol(const struct sk_buff *skb, __be16 proto,
}
break;
case htons(ETH_P_PPP_SES):
- if (nf_flow_pppoe_proto(skb) == proto) {
+ if (nf_flow_pppoe_proto(skb, &inner_proto) &&
+ inner_proto == proto) {
*offset += PPPOE_SES_HLEN;
return true;
}
@@ -310,7 +312,7 @@ static void nf_flow_encap_pop(struct sk_buff *skb,
skb_reset_network_header(skb);
break;
case htons(ETH_P_PPP_SES):
- skb->protocol = nf_flow_pppoe_proto(skb);
+ skb->protocol = __nf_flow_pppoe_proto(skb);
skb_pull(skb, PPPOE_SES_HLEN);
skb_reset_network_header(skb);
break;
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 8d38cd504..1c4b7a8ec 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -1192,6 +1192,24 @@ static void nf_tables_table_disable(struct net *net, struct nft_table *table)
#define __NFT_TABLE_F_UPDATE (__NFT_TABLE_F_WAS_DORMANT | \
__NFT_TABLE_F_WAS_AWAKEN)
+static bool nft_table_pending_update(const struct nft_ctx *ctx)
+{
+ struct nftables_pernet *nft_net = nft_pernet(ctx->net);
+ struct nft_trans *trans;
+
+ if (ctx->table->flags & __NFT_TABLE_F_UPDATE)
+ return true;
+
+ list_for_each_entry(trans, &nft_net->commit_list, list) {
+ if (trans->ctx.table == ctx->table &&
+ trans->msg_type == NFT_MSG_DELCHAIN &&
+ nft_is_base_chain(trans->ctx.chain))
+ return true;
+ }
+
+ return false;
+}
+
static int nf_tables_updtable(struct nft_ctx *ctx)
{
struct nft_trans *trans;
@@ -1215,7 +1233,7 @@ static int nf_tables_updtable(struct nft_ctx *ctx)
return -EOPNOTSUPP;
/* No dormant off/on/off/on games in single transaction */
- if (ctx->table->flags & __NFT_TABLE_F_UPDATE)
+ if (nft_table_pending_update(ctx))
return -EINVAL;
trans = nft_trans_alloc(ctx, NFT_MSG_NEWTABLE,
@@ -2873,7 +2891,7 @@ static const struct nft_expr_type *__nft_expr_type_get(u8 family,
{
const struct nft_expr_type *type, *candidate = NULL;
- list_for_each_entry(type, &nf_tables_expressions, list) {
+ list_for_each_entry_rcu(type, &nf_tables_expressions, list) {
if (!nla_strcmp(nla, type->name)) {
if (!type->family && !candidate)
candidate = type;
@@ -2905,9 +2923,13 @@ static const struct nft_expr_type *nft_expr_type_get(struct net *net,
if (nla == NULL)
return ERR_PTR(-EINVAL);
+ rcu_read_lock();
type = __nft_expr_type_get(family, nla);
- if (type != NULL && try_module_get(type->owner))
+ if (type != NULL && try_module_get(type->owner)) {
+ rcu_read_unlock();
return type;
+ }
+ rcu_read_unlock();
lockdep_nfnl_nft_mutex_not_held();
#ifdef CONFIG_MODULES
@@ -7153,7 +7175,7 @@ static const struct nft_object_type *__nft_obj_type_get(u32 objtype, u8 family)
{
const struct nft_object_type *type;
- list_for_each_entry(type, &nf_tables_objects, list) {
+ list_for_each_entry_rcu(type, &nf_tables_objects, list) {
if (type->family != NFPROTO_UNSPEC &&
type->family != family)
continue;
@@ -7169,9 +7191,13 @@ nft_obj_type_get(struct net *net, u32 objtype, u8 family)
{
const struct nft_object_type *type;
+ rcu_read_lock();
type = __nft_obj_type_get(objtype, family);
- if (type != NULL && try_module_get(type->owner))
+ if (type != NULL && try_module_get(type->owner)) {
+ rcu_read_unlock();
return type;
+ }
+ rcu_read_unlock();
lockdep_nfnl_nft_mutex_not_held();
#ifdef CONFIG_MODULES
@@ -9902,10 +9928,11 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action)
struct nft_trans *trans, *next;
LIST_HEAD(set_update_list);
struct nft_trans_elem *te;
+ int err = 0;
if (action == NFNL_ABORT_VALIDATE &&
nf_tables_validate(net) < 0)
- return -EAGAIN;
+ err = -EAGAIN;
list_for_each_entry_safe_reverse(trans, next, &nft_net->commit_list,
list) {
@@ -10076,12 +10103,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action)
nf_tables_abort_release(trans);
}
- if (action == NFNL_ABORT_AUTOLOAD)
- nf_tables_module_autoload(net);
- else
- nf_tables_module_autoload_cleanup(net);
-
- return 0;
+ return err;
}
static int nf_tables_abort(struct net *net, struct sk_buff *skb,
@@ -10095,6 +10117,16 @@ static int nf_tables_abort(struct net *net, struct sk_buff *skb,
ret = __nf_tables_abort(net, action);
nft_gc_seq_end(nft_net, gc_seq);
+ WARN_ON_ONCE(!list_empty(&nft_net->commit_list));
+
+ /* module autoload needs to happen after GC sequence update because it
+ * temporarily releases and grabs mutex again.
+ */
+ if (action == NFNL_ABORT_AUTOLOAD)
+ nf_tables_module_autoload(net);
+ else
+ nf_tables_module_autoload_cleanup(net);
+
mutex_unlock(&nft_net->commit_mutex);
return ret;
@@ -10892,9 +10924,10 @@ static void __net_exit nf_tables_exit_net(struct net *net)
gc_seq = nft_gc_seq_begin(nft_net);
- if (!list_empty(&nft_net->commit_list) ||
- !list_empty(&nft_net->module_list))
- __nf_tables_abort(net, NFNL_ABORT_NONE);
+ WARN_ON_ONCE(!list_empty(&nft_net->commit_list));
+
+ if (!list_empty(&nft_net->module_list))
+ nf_tables_module_autoload_cleanup(net);
__nft_release_tables(net);
diff --git a/net/netfilter/nft_chain_filter.c b/net/netfilter/nft_chain_filter.c
index 274b6f7e6..d170758a1 100644
--- a/net/netfilter/nft_chain_filter.c
+++ b/net/netfilter/nft_chain_filter.c
@@ -338,7 +338,9 @@ static void nft_netdev_event(unsigned long event, struct net_device *dev,
return;
if (n > 1) {
- nf_unregister_net_hook(ctx->net, &found->ops);
+ if (!(ctx->chain->table->flags & NFT_TABLE_F_DORMANT))
+ nf_unregister_net_hook(ctx->net, &found->ops);
+
list_del_rcu(&found->list);
kfree_rcu(found, rcu);
return;
diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c
index 58eca2616..2299ced93 100644
--- a/net/netfilter/nft_set_pipapo.c
+++ b/net/netfilter/nft_set_pipapo.c
@@ -1994,6 +1994,8 @@ static void nft_pipapo_remove(const struct net *net, const struct nft_set *set,
rules_fx = rules_f0;
nft_pipapo_for_each_field(f, i, m) {
+ bool last = i == m->field_count - 1;
+
if (!pipapo_match_field(f, start, rules_fx,
match_start, match_end))
break;
@@ -2006,16 +2008,18 @@ static void nft_pipapo_remove(const struct net *net, const struct nft_set *set,
match_start += NFT_PIPAPO_GROUPS_PADDED_SIZE(f);
match_end += NFT_PIPAPO_GROUPS_PADDED_SIZE(f);
- }
- if (i == m->field_count) {
- priv->dirty = true;
- pipapo_drop(m, rulemap);
- return;
+ if (last && f->mt[rulemap[i].to].e == e) {
+ priv->dirty = true;
+ pipapo_drop(m, rulemap);
+ return;
+ }
}
first_rule += rules_f0;
}
+
+ WARN_ON_ONCE(1); /* elem_priv not found */
}
/**
diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index 0591cfb28..2302bae1e 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -1711,8 +1711,9 @@ int ovs_ct_copy_action(struct net *net, const struct nlattr *attr,
if (ct_info.timeout[0]) {
if (nf_ct_set_timeout(net, ct_info.ct, family, key->ip.proto,
ct_info.timeout))
- pr_info_ratelimited("Failed to associated timeout "
- "policy `%s'\n", ct_info.timeout);
+ OVS_NLERR(log,
+ "Failed to associated timeout policy '%s'",
+ ct_info.timeout);
else
ct_info.nf_ct_timeout = rcu_dereference(
nf_ct_timeout_find(ct_info.ct)->timeout);
@@ -1919,9 +1920,9 @@ static void ovs_ct_limit_exit(struct net *net, struct ovs_net *ovs_net)
for (i = 0; i < CT_LIMIT_HASH_BUCKETS; ++i) {
struct hlist_head *head = &info->limits[i];
struct ovs_ct_limit *ct_limit;
+ struct hlist_node *next;
- hlist_for_each_entry_rcu(ct_limit, head, hlist_node,
- lockdep_ovsl_is_held())
+ hlist_for_each_entry_safe(ct_limit, next, head, hlist_node)
kfree_rcu(ct_limit, rcu);
}
kfree(info->limits);
diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c
index 25fb2fd18..21b8bf23e 100644
--- a/net/smc/smc_pnet.c
+++ b/net/smc/smc_pnet.c
@@ -802,6 +802,16 @@ static void smc_pnet_create_pnetids_list(struct net *net)
u8 ndev_pnetid[SMC_MAX_PNETID_LEN];
struct net_device *dev;
+ /* Newly created netns do not have devices.
+ * Do not even acquire rtnl.
+ */
+ if (list_empty(&net->dev_base_head))
+ return;
+
+ /* Note: This might not be needed, because smc_pnet_netdev_event()
+ * is also calling smc_pnet_add_base_pnetid() when handling
+ * NETDEV_UP event.
+ */
rtnl_lock();
for_each_netdev(net, dev)
smc_pnet_add_base_pnetid(net, dev, ndev_pnetid);
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index e1af94393..f28e2956f 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -968,11 +968,11 @@ static struct sock *unix_create1(struct net *net, struct socket *sock, int kern,
sk->sk_write_space = unix_write_space;
sk->sk_max_ack_backlog = net->unx.sysctl_max_dgram_qlen;
sk->sk_destruct = unix_sock_destructor;
- u = unix_sk(sk);
+ u = unix_sk(sk);
+ u->inflight = 0;
u->path.dentry = NULL;
u->path.mnt = NULL;
spin_lock_init(&u->lock);
- atomic_long_set(&u->inflight, 0);
INIT_LIST_HEAD(&u->link);
mutex_init(&u->iolock); /* single task reading lock */
mutex_init(&u->bindlock); /* single task binding lock */
@@ -2675,9 +2675,13 @@ static struct sk_buff *manage_oob(struct sk_buff *skb, struct sock *sk,
WRITE_ONCE(u->oob_skb, NULL);
consume_skb(skb);
}
- } else if (!(flags & MSG_PEEK)) {
+ } else if (flags & MSG_PEEK) {
+ skb = NULL;
+ } else {
skb_unlink(skb, &sk->sk_receive_queue);
- consume_skb(skb);
+ WRITE_ONCE(u->oob_skb, NULL);
+ if (!WARN_ON_ONCE(skb_unref(skb)))
+ kfree_skb(skb);
skb = skb_peek(&sk->sk_receive_queue);
}
}
@@ -2751,18 +2755,16 @@ redo:
last = skb = skb_peek(&sk->sk_receive_queue);
last_len = last ? last->len : 0;
+again:
#if IS_ENABLED(CONFIG_AF_UNIX_OOB)
if (skb) {
skb = manage_oob(skb, sk, flags, copied);
- if (!skb) {
+ if (!skb && copied) {
unix_state_unlock(sk);
- if (copied)
- break;
- goto redo;
+ break;
}
}
#endif
-again:
if (skb == NULL) {
if (copied >= target)
goto unlock;
diff --git a/net/unix/garbage.c b/net/unix/garbage.c
index 9bfffe2a7..d2fc79539 100644
--- a/net/unix/garbage.c
+++ b/net/unix/garbage.c
@@ -166,17 +166,18 @@ static void scan_children(struct sock *x, void (*func)(struct unix_sock *),
static void dec_inflight(struct unix_sock *usk)
{
- atomic_long_dec(&usk->inflight);
+ usk->inflight--;
}
static void inc_inflight(struct unix_sock *usk)
{
- atomic_long_inc(&usk->inflight);
+ usk->inflight++;
}
static void inc_inflight_move_tail(struct unix_sock *u)
{
- atomic_long_inc(&u->inflight);
+ u->inflight++;
+
/* If this still might be part of a cycle, move it to the end
* of the list, so that it's checked even if it was already
* passed over
@@ -234,20 +235,34 @@ void unix_gc(void)
* receive queues. Other, non candidate sockets _can_ be
* added to queue, so we must make sure only to touch
* candidates.
+ *
+ * Embryos, though never candidates themselves, affect which
+ * candidates are reachable by the garbage collector. Before
+ * being added to a listener's queue, an embryo may already
+ * receive data carrying SCM_RIGHTS, potentially making the
+ * passed socket a candidate that is not yet reachable by the
+ * collector. It becomes reachable once the embryo is
+ * enqueued. Therefore, we must ensure that no SCM-laden
+ * embryo appears in a (candidate) listener's queue between
+ * consecutive scan_children() calls.
*/
list_for_each_entry_safe(u, next, &gc_inflight_list, link) {
+ struct sock *sk = &u->sk;
long total_refs;
- long inflight_refs;
- total_refs = file_count(u->sk.sk_socket->file);
- inflight_refs = atomic_long_read(&u->inflight);
+ total_refs = file_count(sk->sk_socket->file);
- BUG_ON(inflight_refs < 1);
- BUG_ON(total_refs < inflight_refs);
- if (total_refs == inflight_refs) {
+ BUG_ON(!u->inflight);
+ BUG_ON(total_refs < u->inflight);
+ if (total_refs == u->inflight) {
list_move_tail(&u->link, &gc_candidates);
__set_bit(UNIX_GC_CANDIDATE, &u->gc_flags);
__set_bit(UNIX_GC_MAYBE_CYCLE, &u->gc_flags);
+
+ if (sk->sk_state == TCP_LISTEN) {
+ unix_state_lock_nested(sk, U_LOCK_GC_LISTENER);
+ unix_state_unlock(sk);
+ }
}
}
@@ -271,7 +286,7 @@ void unix_gc(void)
/* Move cursor to after the current position. */
list_move(&cursor, &u->link);
- if (atomic_long_read(&u->inflight) > 0) {
+ if (u->inflight) {
list_move_tail(&u->link, &not_cycle_list);
__clear_bit(UNIX_GC_MAYBE_CYCLE, &u->gc_flags);
scan_children(&u->sk, inc_inflight_move_tail, NULL);
diff --git a/net/unix/scm.c b/net/unix/scm.c
index d1048b4c2..4eff7da9f 100644
--- a/net/unix/scm.c
+++ b/net/unix/scm.c
@@ -52,12 +52,13 @@ void unix_inflight(struct user_struct *user, struct file *fp)
if (s) {
struct unix_sock *u = unix_sk(s);
- if (atomic_long_inc_return(&u->inflight) == 1) {
+ if (!u->inflight) {
BUG_ON(!list_empty(&u->link));
list_add_tail(&u->link, &gc_inflight_list);
} else {
BUG_ON(list_empty(&u->link));
}
+ u->inflight++;
/* Paired with READ_ONCE() in wait_for_unix_gc() */
WRITE_ONCE(unix_tot_inflight, unix_tot_inflight + 1);
}
@@ -74,10 +75,11 @@ void unix_notinflight(struct user_struct *user, struct file *fp)
if (s) {
struct unix_sock *u = unix_sk(s);
- BUG_ON(!atomic_long_read(&u->inflight));
+ BUG_ON(!u->inflight);
BUG_ON(list_empty(&u->link));
- if (atomic_long_dec_and_test(&u->inflight))
+ u->inflight--;
+ if (!u->inflight)
list_del_init(&u->link);
/* Paired with READ_ONCE() in wait_for_unix_gc() */
WRITE_ONCE(unix_tot_inflight, unix_tot_inflight - 1);
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index 5c8e02d56..e3bdfc517 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -1127,6 +1127,8 @@ static int xsk_setsockopt(struct socket *sock, int level, int optname,
struct xsk_queue **q;
int entries;
+ if (optlen < sizeof(entries))
+ return -EINVAL;
if (copy_from_sockptr(&entries, optval, sizeof(entries)))
return -EFAULT;