summaryrefslogtreecommitdiff
path: root/net
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2026-05-14 08:57:43 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2026-05-14 08:57:43 -0700
commit66182ca873a4e87b3496eca79d57f86b76d7f52d (patch)
treede7036ccfa0347ce8a6476132497d401b1bbdf42 /net
parenteb5441518fba295bd97b59dc54914f89dfaa107d (diff)
parentc78bdba7b9666020c0832150a4fc4c0aebc7c6ac (diff)
downloadlinux-66182ca873a4e87b3496eca79d57f86b76d7f52d.tar.gz
linux-66182ca873a4e87b3496eca79d57f86b76d7f52d.zip
Merge tag 'net-7.1-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
Pull networking fixes from Paolo Abeni: "Including fixes from netfilter. Previous releases - regressions: - ethtool: fix NULL pointer dereference in phy_reply_size - netfilter: - allocate hook ops while under mutex - close dangling table module init race - restore nf_conntrack helper propagation via expectation - tcp: - fix potential UAF in reqsk_timer_handler(). - fix out-of-bounds access for twsk in tcp_ao_established_key(). - vsock: fix empty payload in tap skb for non-linear buffers - hsr: fix NULL pointer dereference in hsr_get_node_data() - eth: - cortina: fix RX drop accounting - ice: fix locking in ice_dcb_rebuild() Previous releases - always broken: - napi: avoid gro timer misfiring at end of busypoll - sched: - dualpi2: initialize timer earlier in dualpi2_init() - sch_cbs: Call qdisc_reset for child qdisc - shaper: - fix ordering issue in net_shaper_commit() - reject handle IDs exceeding internal bit-width - ipv6: flowlabel: enforce per-netns limit for unprivileged callers - tls: fix off-by-one in sg_chain entry count for wrapped sk_msg ring - smc: avoid NULL deref of conn->lnk in smc_msg_event tracepoint - sctp: revalidate list cursor after sctp_sendmsg_to_asoc() in SCTP_SENDALL - batman-adv: - reject new tp_meter sessions during teardown - purge non-released claims - eth: - i40e: cleanup PTP registration on probe failure - idpf: fix double free and use-after-free in aux device error paths - ena: fix potential use-after-free in get_timestamp" * tag 'net-7.1-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (88 commits) net: phy: DP83TC811: add reading of abilities net: tls: prevent chain-after-chain in plain text SG net: tls: fix off-by-one in sg_chain entry count for wrapped sk_msg ring net/smc: reject CHID-0 ACCEPT that matches an empty ism_dev slot macsec: use rcu_work to defer TX SA crypto cleanup out of softirq macsec: use rcu_work to defer RX SA crypto cleanup out of softirq macsec: introduce dedicated workqueue for SA crypto cleanup net: net_failover: Fix the deadlock in slave register MAINTAINERS: update atlantic driver maintainer selftests/tc-testing: Add QFQ/CBS qlen underflow test net/sched: sch_cbs: Call qdisc_reset for child qdisc FDDI: defza: Sanitise the reset safety timer net: ethernet: ravb: Do not check URAM suspension when WoL is active ethtool: fix ethnl_bitmap32_not_zero() bit interval semantics net/smc: avoid NULL deref of conn->lnk in smc_msg_event tracepoint net/smc: fix sleep-inside-lock in __smc_setsockopt() causing local DoS net: atm: fix skb leak in sigd_send() default branch net: ethtool: phy: avoid NULL deref when PHY driver is unbound net: atlantic: preserve PCI wake-from-D3 on shutdown when WOL enabled net: shaper: reject QUEUE scope handle with missing id ...
Diffstat (limited to 'net')
-rw-r--r--net/atm/signaling.c1
-rw-r--r--net/batman-adv/bat_iv_ogm.c85
-rw-r--r--net/batman-adv/bridge_loop_avoidance.c11
-rw-r--r--net/batman-adv/main.c1
-rw-r--r--net/batman-adv/tp_meter.c116
-rw-r--r--net/batman-adv/tp_meter.h1
-rw-r--r--net/batman-adv/types.h4
-rw-r--r--net/bridge/netfilter/ebtable_broute.c14
-rw-r--r--net/bridge/netfilter/ebtable_filter.c14
-rw-r--r--net/bridge/netfilter/ebtable_nat.c12
-rw-r--r--net/bridge/netfilter/ebtables.c71
-rw-r--r--net/core/dev.c21
-rw-r--r--net/core/failover.c6
-rw-r--r--net/ethtool/bitset.c8
-rw-r--r--net/ethtool/phy.c36
-rw-r--r--net/hsr/hsr_framereg.c5
-rw-r--r--net/ipv4/inet_connection_sock.c4
-rw-r--r--net/ipv4/netfilter/arp_tables.c53
-rw-r--r--net/ipv4/netfilter/arptable_filter.c27
-rw-r--r--net/ipv4/netfilter/ip_tables.c59
-rw-r--r--net/ipv4/netfilter/iptable_filter.c27
-rw-r--r--net/ipv4/netfilter/iptable_mangle.c29
-rw-r--r--net/ipv4/netfilter/iptable_nat.c6
-rw-r--r--net/ipv4/netfilter/iptable_raw.c26
-rw-r--r--net/ipv4/netfilter/iptable_security.c27
-rw-r--r--net/ipv4/tcp_ao.c3
-rw-r--r--net/ipv6/ip6_flowlabel.c46
-rw-r--r--net/ipv6/netfilter/ip6_tables.c56
-rw-r--r--net/ipv6/netfilter/ip6table_filter.c26
-rw-r--r--net/ipv6/netfilter/ip6table_mangle.c27
-rw-r--r--net/ipv6/netfilter/ip6table_nat.c6
-rw-r--r--net/ipv6/netfilter/ip6table_raw.c24
-rw-r--r--net/ipv6/netfilter/ip6table_security.c27
-rw-r--r--net/netfilter/nf_conntrack_broadcast.c1
-rw-r--r--net/netfilter/nf_conntrack_core.c7
-rw-r--r--net/netfilter/nf_conntrack_expect.c1
-rw-r--r--net/netfilter/nf_conntrack_h323_main.c12
-rw-r--r--net/netfilter/nf_conntrack_helper.c5
-rw-r--r--net/netfilter/nf_conntrack_netlink.c21
-rw-r--r--net/netfilter/nf_conntrack_sip.c10
-rw-r--r--net/netfilter/nft_ct.c2
-rw-r--r--net/netfilter/x_tables.c177
-rw-r--r--net/netlink/genetlink.c8
-rw-r--r--net/rds/message.c1
-rw-r--r--net/sched/sch_cbs.c16
-rw-r--r--net/sched/sch_dualpi2.c4
-rw-r--r--net/sctp/socket.c9
-rw-r--r--net/shaper/shaper.c166
-rw-r--r--net/shaper/shaper_nl_gen.c7
-rw-r--r--net/shaper/shaper_nl_gen.h2
-rw-r--r--net/smc/af_smc.c20
-rw-r--r--net/smc/smc_tracepoint.h2
-rw-r--r--net/tls/tls_sw.c26
-rw-r--r--net/vmw_vsock/virtio_transport_common.c47
54 files changed, 881 insertions, 542 deletions
diff --git a/net/atm/signaling.c b/net/atm/signaling.c
index 358fbe5e4d1d..b991d937205a 100644
--- a/net/atm/signaling.c
+++ b/net/atm/signaling.c
@@ -179,6 +179,7 @@ as_indicate_complete:
break;
default:
pr_alert("bad message type %d\n", (int)msg->type);
+ dev_kfree_skb(skb);
/* Paired with find_get_vcc(msg->vcc) above */
sock_put(sk);
return -EINVAL;
diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c
index f28e9cbf8ad5..74ef7dc2b2f9 100644
--- a/net/batman-adv/bat_iv_ogm.c
+++ b/net/batman-adv/bat_iv_ogm.c
@@ -173,19 +173,12 @@ free_orig_node_hash:
static struct batadv_neigh_node *
batadv_iv_ogm_neigh_new(struct batadv_hard_iface *hard_iface,
const u8 *neigh_addr,
- struct batadv_orig_node *orig_node,
- struct batadv_orig_node *orig_neigh)
+ struct batadv_orig_node *orig_node)
{
struct batadv_neigh_node *neigh_node;
neigh_node = batadv_neigh_node_get_or_create(orig_node,
hard_iface, neigh_addr);
- if (!neigh_node)
- goto out;
-
- neigh_node->orig_node = orig_neigh;
-
-out:
return neigh_node;
}
@@ -335,7 +328,7 @@ static void batadv_iv_ogm_send_to_if(struct batadv_forw_packet *forw_packet,
struct batadv_priv *bat_priv = netdev_priv(hard_iface->mesh_iface);
const char *fwd_str;
u8 packet_num;
- s16 buff_pos;
+ int buff_pos;
struct batadv_ogm_packet *batadv_ogm_packet;
struct sk_buff *skb;
u8 *packet_pos;
@@ -907,6 +900,31 @@ static u8 batadv_iv_orig_ifinfo_sum(struct batadv_orig_node *orig_node,
}
/**
+ * batadv_iv_ogm_neigh_ifinfo_sum() - Get bcast_own sum for a last-hop neighbor
+ * @bat_priv: the bat priv with all the mesh interface information
+ * @neigh_node: last-hop neighbor of an originator
+ *
+ * Return: Number of replied (rebroadcasted) OGMs for the originator currently
+ * announced by the neighbor. Returns 0 if the neighbor's originator entry is
+ * not available anymore.
+ */
+static u8 batadv_iv_ogm_neigh_ifinfo_sum(struct batadv_priv *bat_priv,
+ const struct batadv_neigh_node *neigh_node)
+{
+ struct batadv_orig_node *orig_neigh;
+ u8 sum;
+
+ orig_neigh = batadv_orig_hash_find(bat_priv, neigh_node->addr);
+ if (!orig_neigh)
+ return 0;
+
+ sum = batadv_iv_orig_ifinfo_sum(orig_neigh, neigh_node->if_incoming);
+ batadv_orig_node_put(orig_neigh);
+
+ return sum;
+}
+
+/**
* batadv_iv_ogm_orig_update() - use OGM to update corresponding data in an
* originator
* @bat_priv: the bat priv with all the mesh interface information
@@ -975,17 +993,9 @@ batadv_iv_ogm_orig_update(struct batadv_priv *bat_priv,
}
if (!neigh_node) {
- struct batadv_orig_node *orig_tmp;
-
- orig_tmp = batadv_iv_ogm_orig_get(bat_priv, ethhdr->h_source);
- if (!orig_tmp)
- goto unlock;
-
neigh_node = batadv_iv_ogm_neigh_new(if_incoming,
ethhdr->h_source,
- orig_node, orig_tmp);
-
- batadv_orig_node_put(orig_tmp);
+ orig_node);
if (!neigh_node)
goto unlock;
} else {
@@ -1037,10 +1047,9 @@ batadv_iv_ogm_orig_update(struct batadv_priv *bat_priv,
*/
if (router_ifinfo &&
neigh_ifinfo->bat_iv.tq_avg == router_ifinfo->bat_iv.tq_avg) {
- sum_orig = batadv_iv_orig_ifinfo_sum(router->orig_node,
- router->if_incoming);
- sum_neigh = batadv_iv_orig_ifinfo_sum(neigh_node->orig_node,
- neigh_node->if_incoming);
+ sum_orig = batadv_iv_ogm_neigh_ifinfo_sum(bat_priv, router);
+ sum_neigh = batadv_iv_ogm_neigh_ifinfo_sum(bat_priv,
+ neigh_node);
if (sum_orig >= sum_neigh)
goto out;
}
@@ -1106,7 +1115,6 @@ static bool batadv_iv_ogm_calc_tq(struct batadv_orig_node *orig_node,
if (!neigh_node)
neigh_node = batadv_iv_ogm_neigh_new(if_incoming,
orig_neigh_node->orig,
- orig_neigh_node,
orig_neigh_node);
if (!neigh_node)
@@ -1303,6 +1311,32 @@ out:
}
/**
+ * batadv_orig_to_direct_router() - get direct next hop neighbor to an orig address
+ * @bat_priv: the bat priv with all the mesh interface information
+ * @orig_addr: the originator MAC address to search the best next hop router for
+ * @if_outgoing: the interface where the OGM should be sent to
+ *
+ * Return: A neighbor node which is the best router towards the given originator
+ * address. Bonding candidates are ignored.
+ */
+static struct batadv_neigh_node *
+batadv_orig_to_direct_router(struct batadv_priv *bat_priv, u8 *orig_addr,
+ struct batadv_hard_iface *if_outgoing)
+{
+ struct batadv_neigh_node *neigh_node;
+ struct batadv_orig_node *orig_node;
+
+ orig_node = batadv_orig_hash_find(bat_priv, orig_addr);
+ if (!orig_node)
+ return NULL;
+
+ neigh_node = batadv_orig_router_get(orig_node, if_outgoing);
+ batadv_orig_node_put(orig_node);
+
+ return neigh_node;
+}
+
+/**
* batadv_iv_ogm_process_per_outif() - process a batman iv OGM for an outgoing
* interface
* @skb: the skb containing the OGM
@@ -1372,8 +1406,9 @@ batadv_iv_ogm_process_per_outif(const struct sk_buff *skb, int ogm_offset,
router = batadv_orig_router_get(orig_node, if_outgoing);
if (router) {
- router_router = batadv_orig_router_get(router->orig_node,
- if_outgoing);
+ router_router = batadv_orig_to_direct_router(bat_priv,
+ router->addr,
+ if_outgoing);
router_ifinfo = batadv_neigh_ifinfo_get(router, if_outgoing);
}
diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c
index 51fe028b9088..cec11f1251d6 100644
--- a/net/batman-adv/bridge_loop_avoidance.c
+++ b/net/batman-adv/bridge_loop_avoidance.c
@@ -318,8 +318,8 @@ batadv_bla_del_backbone_claims(struct batadv_bla_backbone_gw *backbone_gw)
if (claim->backbone_gw != backbone_gw)
continue;
- batadv_claim_put(claim);
hlist_del_rcu(&claim->hash_entry);
+ batadv_claim_put(claim);
}
spin_unlock_bh(list_lock);
}
@@ -723,6 +723,7 @@ static void batadv_bla_add_claim(struct batadv_priv *bat_priv,
if (unlikely(hash_added != 0)) {
/* only local changes happened. */
+ batadv_backbone_gw_put(backbone_gw);
kfree(claim);
return;
}
@@ -1288,6 +1289,13 @@ static void batadv_bla_purge_claims(struct batadv_priv *bat_priv,
rcu_read_lock();
hlist_for_each_entry_rcu(claim, head, hash_entry) {
+ /* only purge claims not currently in the process of being released.
+ * Such claims could otherwise have a NULL-ptr backbone_gw set because
+ * they already went through batadv_claim_release()
+ */
+ if (!kref_get_unless_zero(&claim->refcount))
+ continue;
+
backbone_gw = batadv_bla_claim_get_backbone_gw(claim);
if (now)
goto purge_now;
@@ -1313,6 +1321,7 @@ purge_now:
claim->addr, claim->vid);
skip:
batadv_backbone_gw_put(backbone_gw);
+ batadv_claim_put(claim);
}
rcu_read_unlock();
}
diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c
index 3a35aadd8b41..a4d33ee0fda5 100644
--- a/net/batman-adv/main.c
+++ b/net/batman-adv/main.c
@@ -249,6 +249,7 @@ void batadv_mesh_free(struct net_device *mesh_iface)
atomic_set(&bat_priv->mesh_state, BATADV_MESH_DEACTIVATING);
batadv_purge_outstanding_packets(bat_priv, NULL);
+ batadv_tp_stop_all(bat_priv);
batadv_gw_node_free(bat_priv);
diff --git a/net/batman-adv/tp_meter.c b/net/batman-adv/tp_meter.c
index 2e42f6b348c8..066c76113fc4 100644
--- a/net/batman-adv/tp_meter.c
+++ b/net/batman-adv/tp_meter.c
@@ -12,6 +12,7 @@
#include <linux/byteorder/generic.h>
#include <linux/cache.h>
#include <linux/compiler.h>
+#include <linux/completion.h>
#include <linux/container_of.h>
#include <linux/err.h>
#include <linux/etherdevice.h>
@@ -365,23 +366,38 @@ static void batadv_tp_vars_put(struct batadv_tp_vars *tp_vars)
}
/**
- * batadv_tp_sender_cleanup() - cleanup sender data and drop and timer
- * @bat_priv: the bat priv with all the mesh interface information
- * @tp_vars: the private data of the current TP meter session to cleanup
+ * batadv_tp_list_detach() - remove tp session from mesh session list once
+ * @tp_vars: the private data of the current TP meter session
*/
-static void batadv_tp_sender_cleanup(struct batadv_priv *bat_priv,
- struct batadv_tp_vars *tp_vars)
+static void batadv_tp_list_detach(struct batadv_tp_vars *tp_vars)
{
- cancel_delayed_work(&tp_vars->finish_work);
+ bool detached = false;
spin_lock_bh(&tp_vars->bat_priv->tp_list_lock);
- hlist_del_rcu(&tp_vars->list);
+ if (!hlist_unhashed(&tp_vars->list)) {
+ hlist_del_init_rcu(&tp_vars->list);
+ detached = true;
+ }
spin_unlock_bh(&tp_vars->bat_priv->tp_list_lock);
+ if (!detached)
+ return;
+
+ atomic_dec(&tp_vars->bat_priv->tp_num);
+
/* drop list reference */
batadv_tp_vars_put(tp_vars);
+}
- atomic_dec(&tp_vars->bat_priv->tp_num);
+/**
+ * batadv_tp_sender_cleanup() - cleanup sender data and drop and timer
+ * @tp_vars: the private data of the current TP meter session to cleanup
+ */
+static void batadv_tp_sender_cleanup(struct batadv_tp_vars *tp_vars)
+{
+ cancel_delayed_work_sync(&tp_vars->finish_work);
+
+ batadv_tp_list_detach(tp_vars);
/* kill the timer and remove its reference */
timer_delete_sync(&tp_vars->timer);
@@ -886,7 +902,8 @@ out:
batadv_orig_node_put(orig_node);
batadv_tp_sender_end(bat_priv, tp_vars);
- batadv_tp_sender_cleanup(bat_priv, tp_vars);
+ batadv_tp_sender_cleanup(tp_vars);
+ complete(&tp_vars->finished);
batadv_tp_vars_put(tp_vars);
@@ -918,7 +935,8 @@ static void batadv_tp_start_kthread(struct batadv_tp_vars *tp_vars)
batadv_tp_vars_put(tp_vars);
/* cleanup of failed tp meter variables */
- batadv_tp_sender_cleanup(bat_priv, tp_vars);
+ batadv_tp_sender_cleanup(tp_vars);
+ complete(&tp_vars->finished);
return;
}
@@ -947,6 +965,13 @@ void batadv_tp_start(struct batadv_priv *bat_priv, const u8 *dst,
/* look for an already existing test towards this node */
spin_lock_bh(&bat_priv->tp_list_lock);
+ if (atomic_read(&bat_priv->mesh_state) != BATADV_MESH_ACTIVE) {
+ spin_unlock_bh(&bat_priv->tp_list_lock);
+ batadv_tp_batctl_error_notify(BATADV_TP_REASON_DST_UNREACHABLE,
+ dst, bat_priv, session_cookie);
+ return;
+ }
+
tp_vars = batadv_tp_list_find(bat_priv, dst);
if (tp_vars) {
spin_unlock_bh(&bat_priv->tp_list_lock);
@@ -969,6 +994,7 @@ void batadv_tp_start(struct batadv_priv *bat_priv, const u8 *dst,
tp_vars = kmalloc_obj(*tp_vars, GFP_ATOMIC);
if (!tp_vars) {
+ atomic_dec(&bat_priv->tp_num);
spin_unlock_bh(&bat_priv->tp_list_lock);
batadv_dbg(BATADV_DBG_TP_METER, bat_priv,
"Meter: %s cannot allocate list elements\n",
@@ -1017,6 +1043,7 @@ void batadv_tp_start(struct batadv_priv *bat_priv, const u8 *dst,
tp_vars->start_time = jiffies;
init_waitqueue_head(&tp_vars->more_bytes);
+ init_completion(&tp_vars->finished);
spin_lock_init(&tp_vars->unacked_lock);
INIT_LIST_HEAD(&tp_vars->unacked_list);
@@ -1119,14 +1146,7 @@ static void batadv_tp_receiver_shutdown(struct timer_list *t)
"Shutting down for inactivity (more than %dms) from %pM\n",
BATADV_TP_RECV_TIMEOUT, tp_vars->other_end);
- spin_lock_bh(&tp_vars->bat_priv->tp_list_lock);
- hlist_del_rcu(&tp_vars->list);
- spin_unlock_bh(&tp_vars->bat_priv->tp_list_lock);
-
- /* drop list reference */
- batadv_tp_vars_put(tp_vars);
-
- atomic_dec(&bat_priv->tp_num);
+ batadv_tp_list_detach(tp_vars);
spin_lock_bh(&tp_vars->unacked_lock);
list_for_each_entry_safe(un, safe, &tp_vars->unacked_list, list) {
@@ -1329,9 +1349,12 @@ static struct batadv_tp_vars *
batadv_tp_init_recv(struct batadv_priv *bat_priv,
const struct batadv_icmp_tp_packet *icmp)
{
- struct batadv_tp_vars *tp_vars;
+ struct batadv_tp_vars *tp_vars = NULL;
spin_lock_bh(&bat_priv->tp_list_lock);
+ if (atomic_read(&bat_priv->mesh_state) != BATADV_MESH_ACTIVE)
+ goto out_unlock;
+
tp_vars = batadv_tp_list_find_session(bat_priv, icmp->orig,
icmp->session);
if (tp_vars)
@@ -1344,8 +1367,10 @@ batadv_tp_init_recv(struct batadv_priv *bat_priv,
}
tp_vars = kmalloc_obj(*tp_vars, GFP_ATOMIC);
- if (!tp_vars)
+ if (!tp_vars) {
+ atomic_dec(&bat_priv->tp_num);
goto out_unlock;
+ }
ether_addr_copy(tp_vars->other_end, icmp->orig);
tp_vars->role = BATADV_TP_RECEIVER;
@@ -1464,6 +1489,9 @@ void batadv_tp_meter_recv(struct batadv_priv *bat_priv, struct sk_buff *skb)
{
struct batadv_icmp_tp_packet *icmp;
+ if (atomic_read(&bat_priv->mesh_state) != BATADV_MESH_ACTIVE)
+ goto out;
+
icmp = (struct batadv_icmp_tp_packet *)skb->data;
switch (icmp->subtype) {
@@ -1478,10 +1506,58 @@ void batadv_tp_meter_recv(struct batadv_priv *bat_priv, struct sk_buff *skb)
"Received unknown TP Metric packet type %u\n",
icmp->subtype);
}
+
+out:
consume_skb(skb);
}
/**
+ * batadv_tp_stop_all() - stop all currently running tp meter sessions
+ * @bat_priv: the bat priv with all the mesh interface information
+ */
+void batadv_tp_stop_all(struct batadv_priv *bat_priv)
+{
+ struct batadv_tp_vars *tp_vars[BATADV_TP_MAX_NUM];
+ struct batadv_tp_vars *tp_var;
+ size_t count = 0;
+ size_t i;
+
+ spin_lock_bh(&bat_priv->tp_list_lock);
+ hlist_for_each_entry(tp_var, &bat_priv->tp_list, list) {
+ if (WARN_ON_ONCE(count >= BATADV_TP_MAX_NUM))
+ break;
+
+ if (!kref_get_unless_zero(&tp_var->refcount))
+ continue;
+
+ tp_vars[count++] = tp_var;
+ }
+ spin_unlock_bh(&bat_priv->tp_list_lock);
+
+ for (i = 0; i < count; i++) {
+ tp_var = tp_vars[i];
+
+ switch (tp_var->role) {
+ case BATADV_TP_SENDER:
+ batadv_tp_sender_shutdown(tp_var,
+ BATADV_TP_REASON_CANCEL);
+ wake_up(&tp_var->more_bytes);
+ wait_for_completion(&tp_var->finished);
+ break;
+ case BATADV_TP_RECEIVER:
+ batadv_tp_list_detach(tp_var);
+ if (timer_shutdown_sync(&tp_var->timer))
+ batadv_tp_vars_put(tp_var);
+ break;
+ }
+
+ batadv_tp_vars_put(tp_var);
+ }
+
+ synchronize_net();
+}
+
+/**
* batadv_tp_meter_init() - initialize global tp_meter structures
*/
void __init batadv_tp_meter_init(void)
diff --git a/net/batman-adv/tp_meter.h b/net/batman-adv/tp_meter.h
index f0046d366eac..4e97cd10cd02 100644
--- a/net/batman-adv/tp_meter.h
+++ b/net/batman-adv/tp_meter.h
@@ -17,6 +17,7 @@ void batadv_tp_start(struct batadv_priv *bat_priv, const u8 *dst,
u32 test_length, u32 *cookie);
void batadv_tp_stop(struct batadv_priv *bat_priv, const u8 *dst,
u8 return_value);
+void batadv_tp_stop_all(struct batadv_priv *bat_priv);
void batadv_tp_meter_recv(struct batadv_priv *bat_priv, struct sk_buff *skb);
#endif /* _NET_BATMAN_ADV_TP_METER_H_ */
diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h
index 8fc5fe0e9b05..daa06f421154 100644
--- a/net/batman-adv/types.h
+++ b/net/batman-adv/types.h
@@ -14,6 +14,7 @@
#include <linux/average.h>
#include <linux/bitops.h>
#include <linux/compiler.h>
+#include <linux/completion.h>
#include <linux/if.h>
#include <linux/if_ether.h>
#include <linux/kref.h>
@@ -1328,6 +1329,9 @@ struct batadv_tp_vars {
/** @finish_work: work item for the finishing procedure */
struct delayed_work finish_work;
+ /** @finished: completion signaled when a sender thread exits */
+ struct completion finished;
+
/** @test_length: test length in milliseconds */
u32 test_length;
diff --git a/net/bridge/netfilter/ebtable_broute.c b/net/bridge/netfilter/ebtable_broute.c
index 741360219552..f05c79f215ea 100644
--- a/net/bridge/netfilter/ebtable_broute.c
+++ b/net/bridge/netfilter/ebtable_broute.c
@@ -112,24 +112,22 @@ static struct pernet_operations broute_net_ops = {
static int __init ebtable_broute_init(void)
{
- int ret = ebt_register_template(&broute_table, broute_table_init);
+ int ret = register_pernet_subsys(&broute_net_ops);
if (ret)
return ret;
- ret = register_pernet_subsys(&broute_net_ops);
- if (ret) {
- ebt_unregister_template(&broute_table);
- return ret;
- }
+ ret = ebt_register_template(&broute_table, broute_table_init);
+ if (ret)
+ unregister_pernet_subsys(&broute_net_ops);
- return 0;
+ return ret;
}
static void __exit ebtable_broute_fini(void)
{
- unregister_pernet_subsys(&broute_net_ops);
ebt_unregister_template(&broute_table);
+ unregister_pernet_subsys(&broute_net_ops);
}
module_init(ebtable_broute_init);
diff --git a/net/bridge/netfilter/ebtable_filter.c b/net/bridge/netfilter/ebtable_filter.c
index dacd81b12e62..0fc03b07e62a 100644
--- a/net/bridge/netfilter/ebtable_filter.c
+++ b/net/bridge/netfilter/ebtable_filter.c
@@ -93,24 +93,22 @@ static struct pernet_operations frame_filter_net_ops = {
static int __init ebtable_filter_init(void)
{
- int ret = ebt_register_template(&frame_filter, frame_filter_table_init);
+ int ret = register_pernet_subsys(&frame_filter_net_ops);
if (ret)
return ret;
- ret = register_pernet_subsys(&frame_filter_net_ops);
- if (ret) {
- ebt_unregister_template(&frame_filter);
- return ret;
- }
+ ret = ebt_register_template(&frame_filter, frame_filter_table_init);
+ if (ret)
+ unregister_pernet_subsys(&frame_filter_net_ops);
- return 0;
+ return ret;
}
static void __exit ebtable_filter_fini(void)
{
- unregister_pernet_subsys(&frame_filter_net_ops);
ebt_unregister_template(&frame_filter);
+ unregister_pernet_subsys(&frame_filter_net_ops);
}
module_init(ebtable_filter_init);
diff --git a/net/bridge/netfilter/ebtable_nat.c b/net/bridge/netfilter/ebtable_nat.c
index 0f2a8c6118d4..8a10375d8909 100644
--- a/net/bridge/netfilter/ebtable_nat.c
+++ b/net/bridge/netfilter/ebtable_nat.c
@@ -93,24 +93,22 @@ static struct pernet_operations frame_nat_net_ops = {
static int __init ebtable_nat_init(void)
{
- int ret = ebt_register_template(&frame_nat, frame_nat_table_init);
+ int ret = register_pernet_subsys(&frame_nat_net_ops);
if (ret)
return ret;
- ret = register_pernet_subsys(&frame_nat_net_ops);
- if (ret) {
- ebt_unregister_template(&frame_nat);
- return ret;
- }
+ ret = ebt_register_template(&frame_nat, frame_nat_table_init);
+ if (ret)
+ unregister_pernet_subsys(&frame_nat_net_ops);
return ret;
}
static void __exit ebtable_nat_fini(void)
{
- unregister_pernet_subsys(&frame_nat_net_ops);
ebt_unregister_template(&frame_nat);
+ unregister_pernet_subsys(&frame_nat_net_ops);
}
module_init(ebtable_nat_init);
diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c
index aea3e19875c6..b9f4daac09af 100644
--- a/net/bridge/netfilter/ebtables.c
+++ b/net/bridge/netfilter/ebtables.c
@@ -42,6 +42,7 @@
struct ebt_pernet {
struct list_head tables;
+ struct list_head dead_tables;
};
struct ebt_template {
@@ -1162,11 +1163,6 @@ free_newinfo:
static void __ebt_unregister_table(struct net *net, struct ebt_table *table)
{
- mutex_lock(&ebt_mutex);
- list_del(&table->list);
- mutex_unlock(&ebt_mutex);
- audit_log_nfcfg(table->name, AF_BRIDGE, table->private->nentries,
- AUDIT_XT_OP_UNREGISTER, GFP_KERNEL);
EBT_ENTRY_ITERATE(table->private->entries, table->private->entries_size,
ebt_cleanup_entry, net, NULL);
if (table->private->nentries)
@@ -1267,13 +1263,15 @@ int ebt_register_table(struct net *net, const struct ebt_table *input_table,
for (i = 0; i < num_ops; i++)
ops[i].priv = table;
- list_add(&table->list, &ebt_net->tables);
- mutex_unlock(&ebt_mutex);
-
table->ops = ops;
ret = nf_register_net_hooks(net, ops, num_ops);
- if (ret)
+ if (ret) {
+ synchronize_rcu();
__ebt_unregister_table(net, table);
+ } else {
+ list_add(&table->list, &ebt_net->tables);
+ }
+ mutex_unlock(&ebt_mutex);
audit_log_nfcfg(repl->name, AF_BRIDGE, repl->nentries,
AUDIT_XT_OP_REGISTER, GFP_KERNEL);
@@ -1339,7 +1337,7 @@ void ebt_unregister_template(const struct ebt_table *t)
}
EXPORT_SYMBOL(ebt_unregister_template);
-static struct ebt_table *__ebt_find_table(struct net *net, const char *name)
+void ebt_unregister_table_pre_exit(struct net *net, const char *name)
{
struct ebt_pernet *ebt_net = net_generic(net, ebt_pernet_id);
struct ebt_table *t;
@@ -1348,30 +1346,36 @@ static struct ebt_table *__ebt_find_table(struct net *net, const char *name)
list_for_each_entry(t, &ebt_net->tables, list) {
if (strcmp(t->name, name) == 0) {
+ list_move(&t->list, &ebt_net->dead_tables);
mutex_unlock(&ebt_mutex);
- return t;
+ nf_unregister_net_hooks(net, t->ops, hweight32(t->valid_hooks));
+ return;
}
}
mutex_unlock(&ebt_mutex);
- return NULL;
-}
-
-void ebt_unregister_table_pre_exit(struct net *net, const char *name)
-{
- struct ebt_table *table = __ebt_find_table(net, name);
-
- if (table)
- nf_unregister_net_hooks(net, table->ops, hweight32(table->valid_hooks));
}
EXPORT_SYMBOL(ebt_unregister_table_pre_exit);
void ebt_unregister_table(struct net *net, const char *name)
{
- struct ebt_table *table = __ebt_find_table(net, name);
+ struct ebt_pernet *ebt_net = net_generic(net, ebt_pernet_id);
+ struct ebt_table *t;
- if (table)
- __ebt_unregister_table(net, table);
+ mutex_lock(&ebt_mutex);
+
+ list_for_each_entry(t, &ebt_net->dead_tables, list) {
+ if (strcmp(t->name, name) == 0) {
+ list_del(&t->list);
+ audit_log_nfcfg(t->name, AF_BRIDGE, t->private->nentries,
+ AUDIT_XT_OP_UNREGISTER, GFP_KERNEL);
+ __ebt_unregister_table(net, t);
+ mutex_unlock(&ebt_mutex);
+ return;
+ }
+ }
+
+ mutex_unlock(&ebt_mutex);
}
/* userspace just supplied us with counters */
@@ -2556,11 +2560,21 @@ static int __net_init ebt_pernet_init(struct net *net)
struct ebt_pernet *ebt_net = net_generic(net, ebt_pernet_id);
INIT_LIST_HEAD(&ebt_net->tables);
+ INIT_LIST_HEAD(&ebt_net->dead_tables);
return 0;
}
+static void __net_exit ebt_pernet_exit(struct net *net)
+{
+ struct ebt_pernet *ebt_net = net_generic(net, ebt_pernet_id);
+
+ WARN_ON_ONCE(!list_empty(&ebt_net->tables));
+ WARN_ON_ONCE(!list_empty(&ebt_net->dead_tables));
+}
+
static struct pernet_operations ebt_net_ops = {
.init = ebt_pernet_init,
+ .exit = ebt_pernet_exit,
.id = &ebt_pernet_id,
.size = sizeof(struct ebt_pernet),
};
@@ -2569,19 +2583,20 @@ static int __init ebtables_init(void)
{
int ret;
- ret = xt_register_target(&ebt_standard_target);
+ ret = register_pernet_subsys(&ebt_net_ops);
if (ret < 0)
return ret;
- ret = nf_register_sockopt(&ebt_sockopts);
+
+ ret = xt_register_target(&ebt_standard_target);
if (ret < 0) {
- xt_unregister_target(&ebt_standard_target);
+ unregister_pernet_subsys(&ebt_net_ops);
return ret;
}
- ret = register_pernet_subsys(&ebt_net_ops);
+ ret = nf_register_sockopt(&ebt_sockopts);
if (ret < 0) {
- nf_unregister_sockopt(&ebt_sockopts);
xt_unregister_target(&ebt_standard_target);
+ unregister_pernet_subsys(&ebt_net_ops);
return ret;
}
diff --git a/net/core/dev.c b/net/core/dev.c
index 8bfa8313ef62..0c6c270d9f7d 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -6862,9 +6862,9 @@ static void skb_defer_free_flush(void)
#if defined(CONFIG_NET_RX_BUSY_POLL)
-static void __busy_poll_stop(struct napi_struct *napi, bool skip_schedule)
+static void __busy_poll_stop(struct napi_struct *napi, unsigned long timeout)
{
- if (!skip_schedule) {
+ if (!timeout) {
gro_normal_list(&napi->gro);
__napi_schedule(napi);
return;
@@ -6874,6 +6874,8 @@ static void __busy_poll_stop(struct napi_struct *napi, bool skip_schedule)
gro_flush_normal(&napi->gro, HZ >= 1000);
clear_bit(NAPI_STATE_SCHED, &napi->state);
+ hrtimer_start(&napi->timer, ns_to_ktime(timeout),
+ HRTIMER_MODE_REL_PINNED);
}
enum {
@@ -6885,8 +6887,7 @@ static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock,
unsigned flags, u16 budget)
{
struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx;
- bool skip_schedule = false;
- unsigned long timeout;
+ unsigned long timeout = 0;
int rc;
/* Busy polling means there is a high chance device driver hard irq
@@ -6906,10 +6907,12 @@ static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock,
if (flags & NAPI_F_PREFER_BUSY_POLL) {
napi->defer_hard_irqs_count = napi_get_defer_hard_irqs(napi);
- timeout = napi_get_gro_flush_timeout(napi);
- if (napi->defer_hard_irqs_count && timeout) {
- hrtimer_start(&napi->timer, ns_to_ktime(timeout), HRTIMER_MODE_REL_PINNED);
- skip_schedule = true;
+ if (napi->defer_hard_irqs_count) {
+ /* A short enough gro flush timeout and long enough
+ * poll can result in timer firing too early.
+ * Timer will be armed later if necessary.
+ */
+ timeout = napi_get_gro_flush_timeout(napi);
}
}
@@ -6924,7 +6927,7 @@ static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock,
trace_napi_poll(napi, rc, budget);
netpoll_poll_unlock(have_poll_lock);
if (rc == budget)
- __busy_poll_stop(napi, skip_schedule);
+ __busy_poll_stop(napi, timeout);
bpf_net_ctx_clear(bpf_net_ctx);
local_bh_enable();
}
diff --git a/net/core/failover.c b/net/core/failover.c
index 11bb183c7a1b..e43c59cd6868 100644
--- a/net/core/failover.c
+++ b/net/core/failover.c
@@ -12,6 +12,7 @@
#include <uapi/linux/if_arp.h>
#include <linux/rtnetlink.h>
#include <linux/if_vlan.h>
+#include <net/netdev_lock.h>
#include <net/failover.h>
static LIST_HEAD(failover_list);
@@ -221,8 +222,11 @@ failover_existing_slave_register(struct net_device *failover_dev)
for_each_netdev(net, dev) {
if (netif_is_failover(dev))
continue;
- if (ether_addr_equal(failover_dev->perm_addr, dev->perm_addr))
+ if (ether_addr_equal(failover_dev->perm_addr, dev->perm_addr)) {
+ netdev_lock_ops(dev);
failover_slave_register(dev);
+ netdev_unlock_ops(dev);
+ }
}
rtnl_unlock();
}
diff --git a/net/ethtool/bitset.c b/net/ethtool/bitset.c
index 8bb98d3ea3db..a3a2cc6480a0 100644
--- a/net/ethtool/bitset.c
+++ b/net/ethtool/bitset.c
@@ -92,7 +92,7 @@ static bool ethnl_bitmap32_not_zero(const u32 *map, unsigned int start,
u32 mask;
if (end <= start)
- return true;
+ return false;
if (start % 32) {
mask = ethnl_upper_bits(start);
@@ -105,11 +105,11 @@ static bool ethnl_bitmap32_not_zero(const u32 *map, unsigned int start,
start_word++;
}
- if (!memchr_inv(map + start_word, '\0',
- (end_word - start_word) * sizeof(u32)))
+ if (memchr_inv(map + start_word, '\0',
+ (end_word - start_word) * sizeof(u32)))
return true;
if (end % 32 == 0)
- return true;
+ return false;
return map[end_word] & ethnl_lower_bits(end);
}
diff --git a/net/ethtool/phy.c b/net/ethtool/phy.c
index d4e6887055ab..ddc6eab701ed 100644
--- a/net/ethtool/phy.c
+++ b/net/ethtool/phy.c
@@ -76,6 +76,7 @@ static int phy_prepare_data(const struct ethnl_req_info *req_info,
struct nlattr **tb = info->attrs;
struct phy_device_node *pdn;
struct phy_device *phydev;
+ int ret;
/* RTNL is held by the caller */
phydev = ethnl_req_get_phydev(req_info, tb, ETHTOOL_A_PHY_HEADER,
@@ -88,8 +89,19 @@ static int phy_prepare_data(const struct ethnl_req_info *req_info,
return -EOPNOTSUPP;
rep_data->phyindex = phydev->phyindex;
+
rep_data->name = kstrdup(dev_name(&phydev->mdio.dev), GFP_KERNEL);
- rep_data->drvname = kstrdup(phydev->drv->name, GFP_KERNEL);
+ if (!rep_data->name)
+ return -ENOMEM;
+
+ if (phydev->drv) {
+ rep_data->drvname = kstrdup(phydev->drv->name, GFP_KERNEL);
+ if (!rep_data->drvname) {
+ ret = -ENOMEM;
+ goto err_free_name;
+ }
+ }
+
rep_data->upstream_type = pdn->upstream_type;
if (pdn->upstream_type == PHY_UPSTREAM_PHY) {
@@ -97,15 +109,33 @@ static int phy_prepare_data(const struct ethnl_req_info *req_info,
rep_data->upstream_index = upstream->phyindex;
}
- if (pdn->parent_sfp_bus)
+ if (pdn->parent_sfp_bus) {
rep_data->upstream_sfp_name = kstrdup(sfp_get_name(pdn->parent_sfp_bus),
GFP_KERNEL);
+ if (!rep_data->upstream_sfp_name) {
+ ret = -ENOMEM;
+ goto err_free_drvname;
+ }
+ }
- if (phydev->sfp_bus)
+ if (phydev->sfp_bus) {
rep_data->downstream_sfp_name = kstrdup(sfp_get_name(phydev->sfp_bus),
GFP_KERNEL);
+ if (!rep_data->downstream_sfp_name) {
+ ret = -ENOMEM;
+ goto err_free_upstream_sfp;
+ }
+ }
return 0;
+
+err_free_upstream_sfp:
+ kfree(rep_data->upstream_sfp_name);
+err_free_drvname:
+ kfree(rep_data->drvname);
+err_free_name:
+ kfree(rep_data->name);
+ return ret;
}
static int phy_fill_reply(struct sk_buff *skb,
diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c
index d09875b33588..124619920d38 100644
--- a/net/hsr/hsr_framereg.c
+++ b/net/hsr/hsr_framereg.c
@@ -889,7 +889,10 @@ int hsr_get_node_data(struct hsr_priv *hsr,
if (node->addr_B_port != HSR_PT_NONE) {
port = hsr_port_get_hsr(hsr, node->addr_B_port);
- *addr_b_ifindex = port->dev->ifindex;
+ if (port)
+ *addr_b_ifindex = port->dev->ifindex;
+ else
+ *addr_b_ifindex = -1;
} else {
*addr_b_ifindex = -1;
}
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 928654c34156..dbcd37dfdc15 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -1108,7 +1108,7 @@ static void reqsk_timer_handler(struct timer_list *t)
if (!inet_ehash_insert(req_to_sk(nreq), req_to_sk(oreq), NULL)) {
/* delete timer */
- __inet_csk_reqsk_queue_drop(sk_listener, nreq, true);
+ __inet_csk_reqsk_queue_drop(sk_listener, nreq, false);
goto no_ownership;
}
@@ -1134,7 +1134,7 @@ no_ownership:
}
drop:
- __inet_csk_reqsk_queue_drop(sk_listener, oreq, true);
+ __inet_csk_reqsk_queue_drop(oreq->rsk_listener, oreq, true);
reqsk_put(oreq);
}
diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index 97ead883e4a1..ad2259678c78 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -1501,13 +1501,11 @@ static int do_arpt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len
static void __arpt_unregister_table(struct net *net, struct xt_table *table)
{
- struct xt_table_info *private;
- void *loc_cpu_entry;
+ struct xt_table_info *private = table->private;
struct module *table_owner = table->me;
+ void *loc_cpu_entry;
struct arpt_entry *iter;
- private = xt_unregister_table(table);
-
/* Decrease module usage counts and free resources */
loc_cpu_entry = private->entries;
xt_entry_foreach(iter, loc_cpu_entry, private->size)
@@ -1515,6 +1513,7 @@ static void __arpt_unregister_table(struct net *net, struct xt_table *table)
if (private->number > private->initial_entries)
module_put(table_owner);
xt_free_table_info(private);
+ kfree(table);
}
int arpt_register_table(struct net *net,
@@ -1522,13 +1521,11 @@ int arpt_register_table(struct net *net,
const struct arpt_replace *repl,
const struct nf_hook_ops *template_ops)
{
- struct nf_hook_ops *ops;
- unsigned int num_ops;
- int ret, i;
- struct xt_table_info *newinfo;
struct xt_table_info bootstrap = {0};
- void *loc_cpu_entry;
+ struct xt_table_info *newinfo;
struct xt_table *new_table;
+ void *loc_cpu_entry;
+ int ret;
newinfo = xt_alloc_table_info(repl->size);
if (!newinfo)
@@ -1543,7 +1540,7 @@ int arpt_register_table(struct net *net,
return ret;
}
- new_table = xt_register_table(net, table, &bootstrap, newinfo);
+ new_table = xt_register_table(net, table, template_ops, &bootstrap, newinfo);
if (IS_ERR(new_table)) {
struct arpt_entry *iter;
@@ -1553,46 +1550,12 @@ int arpt_register_table(struct net *net,
return PTR_ERR(new_table);
}
- num_ops = hweight32(table->valid_hooks);
- if (num_ops == 0) {
- ret = -EINVAL;
- goto out_free;
- }
-
- ops = kmemdup_array(template_ops, num_ops, sizeof(*ops), GFP_KERNEL);
- if (!ops) {
- ret = -ENOMEM;
- goto out_free;
- }
-
- for (i = 0; i < num_ops; i++)
- ops[i].priv = new_table;
-
- new_table->ops = ops;
-
- ret = nf_register_net_hooks(net, ops, num_ops);
- if (ret != 0)
- goto out_free;
-
return ret;
-
-out_free:
- __arpt_unregister_table(net, new_table);
- return ret;
-}
-
-void arpt_unregister_table_pre_exit(struct net *net, const char *name)
-{
- struct xt_table *table = xt_find_table(net, NFPROTO_ARP, name);
-
- if (table)
- nf_unregister_net_hooks(net, table->ops, hweight32(table->valid_hooks));
}
-EXPORT_SYMBOL(arpt_unregister_table_pre_exit);
void arpt_unregister_table(struct net *net, const char *name)
{
- struct xt_table *table = xt_find_table(net, NFPROTO_ARP, name);
+ struct xt_table *table = xt_unregister_table_exit(net, NFPROTO_ARP, name);
if (table)
__arpt_unregister_table(net, table);
diff --git a/net/ipv4/netfilter/arptable_filter.c b/net/ipv4/netfilter/arptable_filter.c
index 78cd5ee24448..370b635e3523 100644
--- a/net/ipv4/netfilter/arptable_filter.c
+++ b/net/ipv4/netfilter/arptable_filter.c
@@ -43,7 +43,7 @@ static int arptable_filter_table_init(struct net *net)
static void __net_exit arptable_filter_net_pre_exit(struct net *net)
{
- arpt_unregister_table_pre_exit(net, "filter");
+ xt_unregister_table_pre_exit(net, NFPROTO_ARP, "filter");
}
static void __net_exit arptable_filter_net_exit(struct net *net)
@@ -58,32 +58,33 @@ static struct pernet_operations arptable_filter_net_ops = {
static int __init arptable_filter_init(void)
{
- int ret = xt_register_template(&packet_filter,
- arptable_filter_table_init);
-
- if (ret < 0)
- return ret;
+ int ret;
arpfilter_ops = xt_hook_ops_alloc(&packet_filter, arpt_do_table);
- if (IS_ERR(arpfilter_ops)) {
- xt_unregister_template(&packet_filter);
+ if (IS_ERR(arpfilter_ops))
return PTR_ERR(arpfilter_ops);
- }
ret = register_pernet_subsys(&arptable_filter_net_ops);
+ if (ret < 0)
+ goto err_free;
+
+ ret = xt_register_template(&packet_filter,
+ arptable_filter_table_init);
if (ret < 0) {
- xt_unregister_template(&packet_filter);
- kfree(arpfilter_ops);
- return ret;
+ unregister_pernet_subsys(&arptable_filter_net_ops);
+ goto err_free;
}
+ return 0;
+err_free:
+ kfree(arpfilter_ops);
return ret;
}
static void __exit arptable_filter_fini(void)
{
- unregister_pernet_subsys(&arptable_filter_net_ops);
xt_unregister_template(&packet_filter);
+ unregister_pernet_subsys(&arptable_filter_net_ops);
kfree(arpfilter_ops);
}
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index 23c8deff8095..5cbdb0815857 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -1704,12 +1704,10 @@ do_ipt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len)
static void __ipt_unregister_table(struct net *net, struct xt_table *table)
{
- struct xt_table_info *private;
- void *loc_cpu_entry;
+ struct xt_table_info *private = table->private;
struct module *table_owner = table->me;
struct ipt_entry *iter;
-
- private = xt_unregister_table(table);
+ void *loc_cpu_entry;
/* Decrease module usage counts and free resources */
loc_cpu_entry = private->entries;
@@ -1718,19 +1716,18 @@ static void __ipt_unregister_table(struct net *net, struct xt_table *table)
if (private->number > private->initial_entries)
module_put(table_owner);
xt_free_table_info(private);
+ kfree(table);
}
int ipt_register_table(struct net *net, const struct xt_table *table,
const struct ipt_replace *repl,
const struct nf_hook_ops *template_ops)
{
- struct nf_hook_ops *ops;
- unsigned int num_ops;
- int ret, i;
- struct xt_table_info *newinfo;
struct xt_table_info bootstrap = {0};
- void *loc_cpu_entry;
+ struct xt_table_info *newinfo;
struct xt_table *new_table;
+ void *loc_cpu_entry;
+ int ret;
newinfo = xt_alloc_table_info(repl->size);
if (!newinfo)
@@ -1745,7 +1742,7 @@ int ipt_register_table(struct net *net, const struct xt_table *table,
return ret;
}
- new_table = xt_register_table(net, table, &bootstrap, newinfo);
+ new_table = xt_register_table(net, table, template_ops, &bootstrap, newinfo);
if (IS_ERR(new_table)) {
struct ipt_entry *iter;
@@ -1755,51 +1752,12 @@ int ipt_register_table(struct net *net, const struct xt_table *table,
return PTR_ERR(new_table);
}
- /* No template? No need to do anything. This is used by 'nat' table, it registers
- * with the nat core instead of the netfilter core.
- */
- if (!template_ops)
- return 0;
-
- num_ops = hweight32(table->valid_hooks);
- if (num_ops == 0) {
- ret = -EINVAL;
- goto out_free;
- }
-
- ops = kmemdup_array(template_ops, num_ops, sizeof(*ops), GFP_KERNEL);
- if (!ops) {
- ret = -ENOMEM;
- goto out_free;
- }
-
- for (i = 0; i < num_ops; i++)
- ops[i].priv = new_table;
-
- new_table->ops = ops;
-
- ret = nf_register_net_hooks(net, ops, num_ops);
- if (ret != 0)
- goto out_free;
-
return ret;
-
-out_free:
- __ipt_unregister_table(net, new_table);
- return ret;
-}
-
-void ipt_unregister_table_pre_exit(struct net *net, const char *name)
-{
- struct xt_table *table = xt_find_table(net, NFPROTO_IPV4, name);
-
- if (table)
- nf_unregister_net_hooks(net, table->ops, hweight32(table->valid_hooks));
}
void ipt_unregister_table_exit(struct net *net, const char *name)
{
- struct xt_table *table = xt_find_table(net, NFPROTO_IPV4, name);
+ struct xt_table *table = xt_unregister_table_exit(net, NFPROTO_IPV4, name);
if (table)
__ipt_unregister_table(net, table);
@@ -1887,7 +1845,6 @@ static void __exit ip_tables_fini(void)
}
EXPORT_SYMBOL(ipt_register_table);
-EXPORT_SYMBOL(ipt_unregister_table_pre_exit);
EXPORT_SYMBOL(ipt_unregister_table_exit);
EXPORT_SYMBOL(ipt_do_table);
module_init(ip_tables_init);
diff --git a/net/ipv4/netfilter/iptable_filter.c b/net/ipv4/netfilter/iptable_filter.c
index 3ab908b74795..672d7da1071d 100644
--- a/net/ipv4/netfilter/iptable_filter.c
+++ b/net/ipv4/netfilter/iptable_filter.c
@@ -61,7 +61,7 @@ static int __net_init iptable_filter_net_init(struct net *net)
static void __net_exit iptable_filter_net_pre_exit(struct net *net)
{
- ipt_unregister_table_pre_exit(net, "filter");
+ xt_unregister_table_pre_exit(net, NFPROTO_IPV4, "filter");
}
static void __net_exit iptable_filter_net_exit(struct net *net)
@@ -77,32 +77,33 @@ static struct pernet_operations iptable_filter_net_ops = {
static int __init iptable_filter_init(void)
{
- int ret = xt_register_template(&packet_filter,
- iptable_filter_table_init);
-
- if (ret < 0)
- return ret;
+ int ret;
filter_ops = xt_hook_ops_alloc(&packet_filter, ipt_do_table);
- if (IS_ERR(filter_ops)) {
- xt_unregister_template(&packet_filter);
+ if (IS_ERR(filter_ops))
return PTR_ERR(filter_ops);
- }
ret = register_pernet_subsys(&iptable_filter_net_ops);
+ if (ret < 0)
+ goto err_free;
+
+ ret = xt_register_template(&packet_filter,
+ iptable_filter_table_init);
if (ret < 0) {
- xt_unregister_template(&packet_filter);
- kfree(filter_ops);
- return ret;
+ unregister_pernet_subsys(&iptable_filter_net_ops);
+ goto err_free;
}
return 0;
+err_free:
+ kfree(filter_ops);
+ return ret;
}
static void __exit iptable_filter_fini(void)
{
- unregister_pernet_subsys(&iptable_filter_net_ops);
xt_unregister_template(&packet_filter);
+ unregister_pernet_subsys(&iptable_filter_net_ops);
kfree(filter_ops);
}
diff --git a/net/ipv4/netfilter/iptable_mangle.c b/net/ipv4/netfilter/iptable_mangle.c
index 385d945d8ebe..13d25d9a4610 100644
--- a/net/ipv4/netfilter/iptable_mangle.c
+++ b/net/ipv4/netfilter/iptable_mangle.c
@@ -96,7 +96,7 @@ static int iptable_mangle_table_init(struct net *net)
static void __net_exit iptable_mangle_net_pre_exit(struct net *net)
{
- ipt_unregister_table_pre_exit(net, "mangle");
+ xt_unregister_table_pre_exit(net, NFPROTO_IPV4, "mangle");
}
static void __net_exit iptable_mangle_net_exit(struct net *net)
@@ -111,32 +111,33 @@ static struct pernet_operations iptable_mangle_net_ops = {
static int __init iptable_mangle_init(void)
{
- int ret = xt_register_template(&packet_mangler,
- iptable_mangle_table_init);
- if (ret < 0)
- return ret;
+ int ret;
mangle_ops = xt_hook_ops_alloc(&packet_mangler, iptable_mangle_hook);
- if (IS_ERR(mangle_ops)) {
- xt_unregister_template(&packet_mangler);
- ret = PTR_ERR(mangle_ops);
- return ret;
- }
+ if (IS_ERR(mangle_ops))
+ return PTR_ERR(mangle_ops);
ret = register_pernet_subsys(&iptable_mangle_net_ops);
+ if (ret < 0)
+ goto err_free;
+
+ ret = xt_register_template(&packet_mangler,
+ iptable_mangle_table_init);
if (ret < 0) {
- xt_unregister_template(&packet_mangler);
- kfree(mangle_ops);
- return ret;
+ unregister_pernet_subsys(&iptable_mangle_net_ops);
+ goto err_free;
}
+ return 0;
+err_free:
+ kfree(mangle_ops);
return ret;
}
static void __exit iptable_mangle_fini(void)
{
- unregister_pernet_subsys(&iptable_mangle_net_ops);
xt_unregister_template(&packet_mangler);
+ unregister_pernet_subsys(&iptable_mangle_net_ops);
kfree(mangle_ops);
}
diff --git a/net/ipv4/netfilter/iptable_nat.c b/net/ipv4/netfilter/iptable_nat.c
index 625a1ca13b1b..a0df72554025 100644
--- a/net/ipv4/netfilter/iptable_nat.c
+++ b/net/ipv4/netfilter/iptable_nat.c
@@ -119,8 +119,11 @@ static int iptable_nat_table_init(struct net *net)
}
ret = ipt_nat_register_lookups(net);
- if (ret < 0)
+ if (ret < 0) {
+ xt_unregister_table_pre_exit(net, NFPROTO_IPV4, "nat");
+ synchronize_rcu();
ipt_unregister_table_exit(net, "nat");
+ }
kfree(repl);
return ret;
@@ -129,6 +132,7 @@ static int iptable_nat_table_init(struct net *net)
static void __net_exit iptable_nat_net_pre_exit(struct net *net)
{
ipt_nat_unregister_lookups(net);
+ xt_unregister_table_pre_exit(net, NFPROTO_IPV4, "nat");
}
static void __net_exit iptable_nat_net_exit(struct net *net)
diff --git a/net/ipv4/netfilter/iptable_raw.c b/net/ipv4/netfilter/iptable_raw.c
index 0e7f53964d0a..2745c22f4034 100644
--- a/net/ipv4/netfilter/iptable_raw.c
+++ b/net/ipv4/netfilter/iptable_raw.c
@@ -53,7 +53,7 @@ static int iptable_raw_table_init(struct net *net)
static void __net_exit iptable_raw_net_pre_exit(struct net *net)
{
- ipt_unregister_table_pre_exit(net, "raw");
+ xt_unregister_table_pre_exit(net, NFPROTO_IPV4, "raw");
}
static void __net_exit iptable_raw_net_exit(struct net *net)
@@ -77,32 +77,32 @@ static int __init iptable_raw_init(void)
pr_info("Enabling raw table before defrag\n");
}
- ret = xt_register_template(table,
- iptable_raw_table_init);
- if (ret < 0)
- return ret;
-
rawtable_ops = xt_hook_ops_alloc(table, ipt_do_table);
- if (IS_ERR(rawtable_ops)) {
- xt_unregister_template(table);
+ if (IS_ERR(rawtable_ops))
return PTR_ERR(rawtable_ops);
- }
ret = register_pernet_subsys(&iptable_raw_net_ops);
+ if (ret < 0)
+ goto err_free;
+
+ ret = xt_register_template(table,
+ iptable_raw_table_init);
if (ret < 0) {
- xt_unregister_template(table);
- kfree(rawtable_ops);
- return ret;
+ unregister_pernet_subsys(&iptable_raw_net_ops);
+ goto err_free;
}
+ return 0;
+err_free:
+ kfree(rawtable_ops);
return ret;
}
static void __exit iptable_raw_fini(void)
{
+ xt_unregister_template(&packet_raw);
unregister_pernet_subsys(&iptable_raw_net_ops);
kfree(rawtable_ops);
- xt_unregister_template(&packet_raw);
}
module_init(iptable_raw_init);
diff --git a/net/ipv4/netfilter/iptable_security.c b/net/ipv4/netfilter/iptable_security.c
index d885443cb267..491894511c54 100644
--- a/net/ipv4/netfilter/iptable_security.c
+++ b/net/ipv4/netfilter/iptable_security.c
@@ -50,7 +50,7 @@ static int iptable_security_table_init(struct net *net)
static void __net_exit iptable_security_net_pre_exit(struct net *net)
{
- ipt_unregister_table_pre_exit(net, "security");
+ xt_unregister_table_pre_exit(net, NFPROTO_IPV4, "security");
}
static void __net_exit iptable_security_net_exit(struct net *net)
@@ -65,33 +65,34 @@ static struct pernet_operations iptable_security_net_ops = {
static int __init iptable_security_init(void)
{
- int ret = xt_register_template(&security_table,
- iptable_security_table_init);
-
- if (ret < 0)
- return ret;
+ int ret;
sectbl_ops = xt_hook_ops_alloc(&security_table, ipt_do_table);
- if (IS_ERR(sectbl_ops)) {
- xt_unregister_template(&security_table);
+ if (IS_ERR(sectbl_ops))
return PTR_ERR(sectbl_ops);
- }
ret = register_pernet_subsys(&iptable_security_net_ops);
+ if (ret < 0)
+ goto err_free;
+
+ ret = xt_register_template(&security_table,
+ iptable_security_table_init);
if (ret < 0) {
- xt_unregister_template(&security_table);
- kfree(sectbl_ops);
- return ret;
+ unregister_pernet_subsys(&iptable_security_net_ops);
+ goto err_free;
}
+ return 0;
+err_free:
+ kfree(sectbl_ops);
return ret;
}
static void __exit iptable_security_fini(void)
{
+ xt_unregister_template(&security_table);
unregister_pernet_subsys(&iptable_security_net_ops);
kfree(sectbl_ops);
- xt_unregister_template(&security_table);
}
module_init(iptable_security_init);
diff --git a/net/ipv4/tcp_ao.c b/net/ipv4/tcp_ao.c
index a97cdf3e6af4..0a4b38b315fe 100644
--- a/net/ipv4/tcp_ao.c
+++ b/net/ipv4/tcp_ao.c
@@ -116,7 +116,8 @@ struct tcp_ao_key *tcp_ao_established_key(const struct sock *sk,
{
struct tcp_ao_key *key;
- hlist_for_each_entry_rcu(key, &ao->head, node, lockdep_sock_is_held(sk)) {
+ hlist_for_each_entry_rcu(key, &ao->head, node,
+ sk_fullsock(sk) && lockdep_sock_is_held(sk)) {
if ((sndid >= 0 && key->sndid != sndid) ||
(rcvid >= 0 && key->rcvid != rcvid))
continue;
diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c
index c92f98c6f6ec..b1ccdf0dc646 100644
--- a/net/ipv6/ip6_flowlabel.c
+++ b/net/ipv6/ip6_flowlabel.c
@@ -36,11 +36,11 @@
/* FL hash table */
#define FL_MAX_PER_SOCK 32
-#define FL_MAX_SIZE 4096
+#define FL_MAX_SIZE 8192
#define FL_HASH_MASK 255
#define FL_HASH(l) (ntohl(l)&FL_HASH_MASK)
-static atomic_t fl_size = ATOMIC_INIT(0);
+static int fl_size;
static struct ip6_flowlabel __rcu *fl_ht[FL_HASH_MASK+1];
static void ip6_fl_gc(struct timer_list *unused);
@@ -162,8 +162,9 @@ static void ip6_fl_gc(struct timer_list *unused)
ttd = fl->expires;
if (time_after_eq(now, ttd)) {
*flp = fl->next;
+ fl_size--;
+ fl->fl_net->ipv6.flowlabel_count--;
fl_free(fl);
- atomic_dec(&fl_size);
continue;
}
if (!sched || time_before(ttd, sched))
@@ -172,7 +173,7 @@ static void ip6_fl_gc(struct timer_list *unused)
flp = &fl->next;
}
}
- if (!sched && atomic_read(&fl_size))
+ if (!sched && fl_size)
sched = now + FL_MAX_LINGER;
if (sched) {
mod_timer(&ip6_fl_gc_timer, sched);
@@ -196,7 +197,8 @@ static void __net_exit ip6_fl_purge(struct net *net)
atomic_read(&fl->users) == 0) {
*flp = fl->next;
fl_free(fl);
- atomic_dec(&fl_size);
+ fl_size--;
+ net->ipv6.flowlabel_count--;
continue;
}
flp = &fl->next;
@@ -210,10 +212,10 @@ static struct ip6_flowlabel *fl_intern(struct net *net,
{
struct ip6_flowlabel *lfl;
+ lockdep_assert_held(&ip6_fl_lock);
+
fl->label = label & IPV6_FLOWLABEL_MASK;
- rcu_read_lock();
- spin_lock_bh(&ip6_fl_lock);
if (label == 0) {
for (;;) {
fl->label = htonl(get_random_u32())&IPV6_FLOWLABEL_MASK;
@@ -235,8 +237,6 @@ static struct ip6_flowlabel *fl_intern(struct net *net,
lfl = __fl_lookup(net, fl->label);
if (lfl) {
atomic_inc(&lfl->users);
- spin_unlock_bh(&ip6_fl_lock);
- rcu_read_unlock();
return lfl;
}
}
@@ -244,9 +244,8 @@ static struct ip6_flowlabel *fl_intern(struct net *net,
fl->lastuse = jiffies;
fl->next = fl_ht[FL_HASH(fl->label)];
rcu_assign_pointer(fl_ht[FL_HASH(fl->label)], fl);
- atomic_inc(&fl_size);
- spin_unlock_bh(&ip6_fl_lock);
- rcu_read_unlock();
+ fl_size++;
+ net->ipv6.flowlabel_count++;
return NULL;
}
@@ -464,10 +463,17 @@ done:
static int mem_check(struct sock *sk)
{
- int room = FL_MAX_SIZE - atomic_read(&fl_size);
+ const int unpriv_total_limit = FL_MAX_SIZE - (FL_MAX_SIZE / 4);
+ const int unpriv_user_limit = unpriv_total_limit / 2;
+ struct net *net = sock_net(sk);
+ int room;
struct ipv6_fl_socklist *sfl;
int count = 0;
+ lockdep_assert_held(&ip6_fl_lock);
+
+ room = FL_MAX_SIZE - fl_size;
+
if (room > FL_MAX_SIZE - FL_MAX_PER_SOCK)
return 0;
@@ -478,7 +484,9 @@ static int mem_check(struct sock *sk)
if (room <= 0 ||
((count >= FL_MAX_PER_SOCK ||
- (count > 0 && room < FL_MAX_SIZE/2) || room < FL_MAX_SIZE/4) &&
+ (count > 0 && room < FL_MAX_SIZE / 2) ||
+ room < FL_MAX_SIZE / 4 ||
+ net->ipv6.flowlabel_count >= unpriv_user_limit) &&
!capable(CAP_NET_ADMIN)))
return -ENOBUFS;
@@ -692,11 +700,19 @@ release:
if (!sfl1)
goto done;
+ rcu_read_lock();
+ spin_lock_bh(&ip6_fl_lock);
err = mem_check(sk);
+ if (err == 0)
+ fl1 = fl_intern(net, fl, freq->flr_label);
+ else
+ fl1 = NULL;
+ spin_unlock_bh(&ip6_fl_lock);
+ rcu_read_unlock();
+
if (err != 0)
goto done;
- fl1 = fl_intern(net, fl, freq->flr_label);
if (fl1)
goto recheck;
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index d585ac3c1113..9d9c3763f2f5 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -1713,12 +1713,10 @@ do_ip6t_get_ctl(struct sock *sk, int cmd, void __user *user, int *len)
static void __ip6t_unregister_table(struct net *net, struct xt_table *table)
{
- struct xt_table_info *private;
- void *loc_cpu_entry;
+ struct xt_table_info *private = table->private;
struct module *table_owner = table->me;
struct ip6t_entry *iter;
-
- private = xt_unregister_table(table);
+ void *loc_cpu_entry;
/* Decrease module usage counts and free resources */
loc_cpu_entry = private->entries;
@@ -1727,19 +1725,18 @@ static void __ip6t_unregister_table(struct net *net, struct xt_table *table)
if (private->number > private->initial_entries)
module_put(table_owner);
xt_free_table_info(private);
+ kfree(table);
}
int ip6t_register_table(struct net *net, const struct xt_table *table,
const struct ip6t_replace *repl,
const struct nf_hook_ops *template_ops)
{
- struct nf_hook_ops *ops;
- unsigned int num_ops;
- int ret, i;
- struct xt_table_info *newinfo;
struct xt_table_info bootstrap = {0};
- void *loc_cpu_entry;
+ struct xt_table_info *newinfo;
struct xt_table *new_table;
+ void *loc_cpu_entry;
+ int ret;
newinfo = xt_alloc_table_info(repl->size);
if (!newinfo)
@@ -1754,7 +1751,7 @@ int ip6t_register_table(struct net *net, const struct xt_table *table,
return ret;
}
- new_table = xt_register_table(net, table, &bootstrap, newinfo);
+ new_table = xt_register_table(net, table, template_ops, &bootstrap, newinfo);
if (IS_ERR(new_table)) {
struct ip6t_entry *iter;
@@ -1764,48 +1761,12 @@ int ip6t_register_table(struct net *net, const struct xt_table *table,
return PTR_ERR(new_table);
}
- if (!template_ops)
- return 0;
-
- num_ops = hweight32(table->valid_hooks);
- if (num_ops == 0) {
- ret = -EINVAL;
- goto out_free;
- }
-
- ops = kmemdup_array(template_ops, num_ops, sizeof(*ops), GFP_KERNEL);
- if (!ops) {
- ret = -ENOMEM;
- goto out_free;
- }
-
- for (i = 0; i < num_ops; i++)
- ops[i].priv = new_table;
-
- new_table->ops = ops;
-
- ret = nf_register_net_hooks(net, ops, num_ops);
- if (ret != 0)
- goto out_free;
-
return ret;
-
-out_free:
- __ip6t_unregister_table(net, new_table);
- return ret;
-}
-
-void ip6t_unregister_table_pre_exit(struct net *net, const char *name)
-{
- struct xt_table *table = xt_find_table(net, NFPROTO_IPV6, name);
-
- if (table)
- nf_unregister_net_hooks(net, table->ops, hweight32(table->valid_hooks));
}
void ip6t_unregister_table_exit(struct net *net, const char *name)
{
- struct xt_table *table = xt_find_table(net, NFPROTO_IPV6, name);
+ struct xt_table *table = xt_unregister_table_exit(net, NFPROTO_IPV6, name);
if (table)
__ip6t_unregister_table(net, table);
@@ -1894,7 +1855,6 @@ static void __exit ip6_tables_fini(void)
}
EXPORT_SYMBOL(ip6t_register_table);
-EXPORT_SYMBOL(ip6t_unregister_table_pre_exit);
EXPORT_SYMBOL(ip6t_unregister_table_exit);
EXPORT_SYMBOL(ip6t_do_table);
diff --git a/net/ipv6/netfilter/ip6table_filter.c b/net/ipv6/netfilter/ip6table_filter.c
index e8992693e14a..b074fc477676 100644
--- a/net/ipv6/netfilter/ip6table_filter.c
+++ b/net/ipv6/netfilter/ip6table_filter.c
@@ -60,7 +60,7 @@ static int __net_init ip6table_filter_net_init(struct net *net)
static void __net_exit ip6table_filter_net_pre_exit(struct net *net)
{
- ip6t_unregister_table_pre_exit(net, "filter");
+ xt_unregister_table_pre_exit(net, NFPROTO_IPV6, "filter");
}
static void __net_exit ip6table_filter_net_exit(struct net *net)
@@ -76,32 +76,32 @@ static struct pernet_operations ip6table_filter_net_ops = {
static int __init ip6table_filter_init(void)
{
- int ret = xt_register_template(&packet_filter,
- ip6table_filter_table_init);
-
- if (ret < 0)
- return ret;
+ int ret;
filter_ops = xt_hook_ops_alloc(&packet_filter, ip6t_do_table);
- if (IS_ERR(filter_ops)) {
- xt_unregister_template(&packet_filter);
+ if (IS_ERR(filter_ops))
return PTR_ERR(filter_ops);
- }
ret = register_pernet_subsys(&ip6table_filter_net_ops);
+ if (ret < 0)
+ goto err_free;
+
+ ret = xt_register_template(&packet_filter, ip6table_filter_table_init);
if (ret < 0) {
- xt_unregister_template(&packet_filter);
- kfree(filter_ops);
- return ret;
+ unregister_pernet_subsys(&ip6table_filter_net_ops);
+ goto err_free;
}
+ return 0;
+err_free:
+ kfree(filter_ops);
return ret;
}
static void __exit ip6table_filter_fini(void)
{
- unregister_pernet_subsys(&ip6table_filter_net_ops);
xt_unregister_template(&packet_filter);
+ unregister_pernet_subsys(&ip6table_filter_net_ops);
kfree(filter_ops);
}
diff --git a/net/ipv6/netfilter/ip6table_mangle.c b/net/ipv6/netfilter/ip6table_mangle.c
index 8dd4cd0c47bd..e6ee036a9b2c 100644
--- a/net/ipv6/netfilter/ip6table_mangle.c
+++ b/net/ipv6/netfilter/ip6table_mangle.c
@@ -89,7 +89,7 @@ static int ip6table_mangle_table_init(struct net *net)
static void __net_exit ip6table_mangle_net_pre_exit(struct net *net)
{
- ip6t_unregister_table_pre_exit(net, "mangle");
+ xt_unregister_table_pre_exit(net, NFPROTO_IPV6, "mangle");
}
static void __net_exit ip6table_mangle_net_exit(struct net *net)
@@ -104,32 +104,33 @@ static struct pernet_operations ip6table_mangle_net_ops = {
static int __init ip6table_mangle_init(void)
{
- int ret = xt_register_template(&packet_mangler,
- ip6table_mangle_table_init);
-
- if (ret < 0)
- return ret;
+ int ret;
mangle_ops = xt_hook_ops_alloc(&packet_mangler, ip6table_mangle_hook);
- if (IS_ERR(mangle_ops)) {
- xt_unregister_template(&packet_mangler);
+ if (IS_ERR(mangle_ops))
return PTR_ERR(mangle_ops);
- }
ret = register_pernet_subsys(&ip6table_mangle_net_ops);
+ if (ret < 0)
+ goto err_free;
+
+ ret = xt_register_template(&packet_mangler,
+ ip6table_mangle_table_init);
if (ret < 0) {
- xt_unregister_template(&packet_mangler);
- kfree(mangle_ops);
- return ret;
+ unregister_pernet_subsys(&ip6table_mangle_net_ops);
+ goto err_free;
}
+ return 0;
+err_free:
+ kfree(mangle_ops);
return ret;
}
static void __exit ip6table_mangle_fini(void)
{
- unregister_pernet_subsys(&ip6table_mangle_net_ops);
xt_unregister_template(&packet_mangler);
+ unregister_pernet_subsys(&ip6table_mangle_net_ops);
kfree(mangle_ops);
}
diff --git a/net/ipv6/netfilter/ip6table_nat.c b/net/ipv6/netfilter/ip6table_nat.c
index 5be723232df8..c2394e2c94b5 100644
--- a/net/ipv6/netfilter/ip6table_nat.c
+++ b/net/ipv6/netfilter/ip6table_nat.c
@@ -121,8 +121,11 @@ static int ip6table_nat_table_init(struct net *net)
}
ret = ip6t_nat_register_lookups(net);
- if (ret < 0)
+ if (ret < 0) {
+ xt_unregister_table_pre_exit(net, NFPROTO_IPV6, "nat");
+ synchronize_rcu();
ip6t_unregister_table_exit(net, "nat");
+ }
kfree(repl);
return ret;
@@ -131,6 +134,7 @@ static int ip6table_nat_table_init(struct net *net)
static void __net_exit ip6table_nat_net_pre_exit(struct net *net)
{
ip6t_nat_unregister_lookups(net);
+ xt_unregister_table_pre_exit(net, NFPROTO_IPV6, "nat");
}
static void __net_exit ip6table_nat_net_exit(struct net *net)
diff --git a/net/ipv6/netfilter/ip6table_raw.c b/net/ipv6/netfilter/ip6table_raw.c
index fc9f6754028f..3b161ee875bc 100644
--- a/net/ipv6/netfilter/ip6table_raw.c
+++ b/net/ipv6/netfilter/ip6table_raw.c
@@ -52,7 +52,7 @@ static int ip6table_raw_table_init(struct net *net)
static void __net_exit ip6table_raw_net_pre_exit(struct net *net)
{
- ip6t_unregister_table_pre_exit(net, "raw");
+ xt_unregister_table_pre_exit(net, NFPROTO_IPV6, "raw");
}
static void __net_exit ip6table_raw_net_exit(struct net *net)
@@ -75,31 +75,31 @@ static int __init ip6table_raw_init(void)
pr_info("Enabling raw table before defrag\n");
}
- ret = xt_register_template(table, ip6table_raw_table_init);
- if (ret < 0)
- return ret;
-
/* Register hooks */
rawtable_ops = xt_hook_ops_alloc(table, ip6t_do_table);
- if (IS_ERR(rawtable_ops)) {
- xt_unregister_template(table);
+ if (IS_ERR(rawtable_ops))
return PTR_ERR(rawtable_ops);
- }
ret = register_pernet_subsys(&ip6table_raw_net_ops);
+ if (ret < 0)
+ goto err_free;
+
+ ret = xt_register_template(table, ip6table_raw_table_init);
if (ret < 0) {
- kfree(rawtable_ops);
- xt_unregister_template(table);
- return ret;
+ unregister_pernet_subsys(&ip6table_raw_net_ops);
+ goto err_free;
}
+ return 0;
+err_free:
+ kfree(rawtable_ops);
return ret;
}
static void __exit ip6table_raw_fini(void)
{
- unregister_pernet_subsys(&ip6table_raw_net_ops);
xt_unregister_template(&packet_raw);
+ unregister_pernet_subsys(&ip6table_raw_net_ops);
kfree(rawtable_ops);
}
diff --git a/net/ipv6/netfilter/ip6table_security.c b/net/ipv6/netfilter/ip6table_security.c
index 4df14a9bae78..4bd5d97b8ab6 100644
--- a/net/ipv6/netfilter/ip6table_security.c
+++ b/net/ipv6/netfilter/ip6table_security.c
@@ -49,7 +49,7 @@ static int ip6table_security_table_init(struct net *net)
static void __net_exit ip6table_security_net_pre_exit(struct net *net)
{
- ip6t_unregister_table_pre_exit(net, "security");
+ xt_unregister_table_pre_exit(net, NFPROTO_IPV6, "security");
}
static void __net_exit ip6table_security_net_exit(struct net *net)
@@ -64,32 +64,33 @@ static struct pernet_operations ip6table_security_net_ops = {
static int __init ip6table_security_init(void)
{
- int ret = xt_register_template(&security_table,
- ip6table_security_table_init);
-
- if (ret < 0)
- return ret;
+ int ret;
sectbl_ops = xt_hook_ops_alloc(&security_table, ip6t_do_table);
- if (IS_ERR(sectbl_ops)) {
- xt_unregister_template(&security_table);
+ if (IS_ERR(sectbl_ops))
return PTR_ERR(sectbl_ops);
- }
ret = register_pernet_subsys(&ip6table_security_net_ops);
+ if (ret < 0)
+ goto err_free;
+
+ ret = xt_register_template(&security_table,
+ ip6table_security_table_init);
if (ret < 0) {
- kfree(sectbl_ops);
- xt_unregister_template(&security_table);
- return ret;
+ unregister_pernet_subsys(&ip6table_security_net_ops);
+ goto err_free;
}
+ return 0;
+err_free:
+ kfree(sectbl_ops);
return ret;
}
static void __exit ip6table_security_fini(void)
{
- unregister_pernet_subsys(&ip6table_security_net_ops);
xt_unregister_template(&security_table);
+ unregister_pernet_subsys(&ip6table_security_net_ops);
kfree(sectbl_ops);
}
diff --git a/net/netfilter/nf_conntrack_broadcast.c b/net/netfilter/nf_conntrack_broadcast.c
index 4f39bf7c843f..75e53fde6b29 100644
--- a/net/netfilter/nf_conntrack_broadcast.c
+++ b/net/netfilter/nf_conntrack_broadcast.c
@@ -72,6 +72,7 @@ int nf_conntrack_broadcast_help(struct sk_buff *skb,
exp->flags = NF_CT_EXPECT_PERMANENT;
exp->class = NF_CT_EXPECT_CLASS_DEFAULT;
rcu_assign_pointer(exp->helper, helper);
+ rcu_assign_pointer(exp->assign_helper, NULL);
write_pnet(&exp->net, net);
#ifdef CONFIG_NF_CONNTRACK_ZONES
exp->zone = ct->zone;
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index b08189226320..8ba5b22a1eef 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -1811,14 +1811,17 @@ init_conntrack(struct net *net, struct nf_conn *tmpl,
spin_lock_bh(&nf_conntrack_expect_lock);
exp = nf_ct_find_expectation(net, zone, tuple, !tmpl || nf_ct_is_confirmed(tmpl));
if (exp) {
+ struct nf_conntrack_helper *assign_helper;
+
/* Welcome, Mr. Bond. We've been expecting you... */
__set_bit(IPS_EXPECTED_BIT, &ct->status);
/* exp->master safe, refcnt bumped in nf_ct_find_expectation */
ct->master = exp->master;
- if (exp->helper) {
+ assign_helper = rcu_dereference(exp->assign_helper);
+ if (assign_helper) {
help = nf_ct_helper_ext_add(ct, GFP_ATOMIC);
if (help)
- rcu_assign_pointer(help->helper, exp->helper);
+ rcu_assign_pointer(help->helper, assign_helper);
}
#ifdef CONFIG_NF_CONNTRACK_MARK
diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c
index 24d0576d84b7..8e943efbdf0a 100644
--- a/net/netfilter/nf_conntrack_expect.c
+++ b/net/netfilter/nf_conntrack_expect.c
@@ -344,6 +344,7 @@ void nf_ct_expect_init(struct nf_conntrack_expect *exp, unsigned int class,
helper = rcu_dereference(help->helper);
rcu_assign_pointer(exp->helper, helper);
+ rcu_assign_pointer(exp->assign_helper, NULL);
write_pnet(&exp->net, net);
#ifdef CONFIG_NF_CONNTRACK_ZONES
exp->zone = ct->zone;
diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c
index 3f5c50455b71..b2fe6554b9cf 100644
--- a/net/netfilter/nf_conntrack_h323_main.c
+++ b/net/netfilter/nf_conntrack_h323_main.c
@@ -643,7 +643,7 @@ static int expect_h245(struct sk_buff *skb, struct nf_conn *ct,
&ct->tuplehash[!dir].tuple.src.u3,
&ct->tuplehash[!dir].tuple.dst.u3,
IPPROTO_TCP, NULL, &port);
- rcu_assign_pointer(exp->helper, &nf_conntrack_helper_h245);
+ rcu_assign_pointer(exp->assign_helper, &nf_conntrack_helper_h245);
nathook = rcu_dereference(nfct_h323_nat_hook);
if (memcmp(&ct->tuplehash[dir].tuple.src.u3,
@@ -767,7 +767,7 @@ static int expect_callforwarding(struct sk_buff *skb,
nf_ct_expect_init(exp, NF_CT_EXPECT_CLASS_DEFAULT, nf_ct_l3num(ct),
&ct->tuplehash[!dir].tuple.src.u3, &addr,
IPPROTO_TCP, NULL, &port);
- rcu_assign_pointer(exp->helper, nf_conntrack_helper_q931);
+ rcu_assign_pointer(exp->assign_helper, nf_conntrack_helper_q931);
nathook = rcu_dereference(nfct_h323_nat_hook);
if (memcmp(&ct->tuplehash[dir].tuple.src.u3,
@@ -1234,7 +1234,7 @@ static int expect_q931(struct sk_buff *skb, struct nf_conn *ct,
&ct->tuplehash[!dir].tuple.src.u3 : NULL,
&ct->tuplehash[!dir].tuple.dst.u3,
IPPROTO_TCP, NULL, &port);
- rcu_assign_pointer(exp->helper, nf_conntrack_helper_q931);
+ rcu_assign_pointer(exp->assign_helper, nf_conntrack_helper_q931);
exp->flags = NF_CT_EXPECT_PERMANENT; /* Accept multiple calls */
nathook = rcu_dereference(nfct_h323_nat_hook);
@@ -1306,7 +1306,7 @@ static int process_gcf(struct sk_buff *skb, struct nf_conn *ct,
nf_ct_expect_init(exp, NF_CT_EXPECT_CLASS_DEFAULT, nf_ct_l3num(ct),
&ct->tuplehash[!dir].tuple.src.u3, &addr,
IPPROTO_UDP, NULL, &port);
- rcu_assign_pointer(exp->helper, nf_conntrack_helper_ras);
+ rcu_assign_pointer(exp->assign_helper, nf_conntrack_helper_ras);
if (nf_ct_expect_related(exp, 0) == 0) {
pr_debug("nf_ct_ras: expect RAS ");
@@ -1523,7 +1523,7 @@ static int process_acf(struct sk_buff *skb, struct nf_conn *ct,
&ct->tuplehash[!dir].tuple.src.u3, &addr,
IPPROTO_TCP, NULL, &port);
exp->flags = NF_CT_EXPECT_PERMANENT;
- rcu_assign_pointer(exp->helper, nf_conntrack_helper_q931);
+ rcu_assign_pointer(exp->assign_helper, nf_conntrack_helper_q931);
if (nf_ct_expect_related(exp, 0) == 0) {
pr_debug("nf_ct_ras: expect Q.931 ");
@@ -1577,7 +1577,7 @@ static int process_lcf(struct sk_buff *skb, struct nf_conn *ct,
&ct->tuplehash[!dir].tuple.src.u3, &addr,
IPPROTO_TCP, NULL, &port);
exp->flags = NF_CT_EXPECT_PERMANENT;
- rcu_assign_pointer(exp->helper, nf_conntrack_helper_q931);
+ rcu_assign_pointer(exp->assign_helper, nf_conntrack_helper_q931);
if (nf_ct_expect_related(exp, 0) == 0) {
pr_debug("nf_ct_ras: expect Q.931 ");
diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c
index a715304a53d8..b594cd244fe1 100644
--- a/net/netfilter/nf_conntrack_helper.c
+++ b/net/netfilter/nf_conntrack_helper.c
@@ -400,6 +400,11 @@ static bool expect_iter_me(struct nf_conntrack_expect *exp, void *data)
this = rcu_dereference_protected(exp->helper,
lockdep_is_held(&nf_conntrack_expect_lock));
+ if (this == me)
+ return true;
+
+ this = rcu_dereference_protected(exp->assign_helper,
+ lockdep_is_held(&nf_conntrack_expect_lock));
return this == me;
}
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index eda5fe4a75c8..befa7e83ee49 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -2634,6 +2634,7 @@ static const struct nla_policy exp_nla_policy[CTA_EXPECT_MAX+1] = {
static struct nf_conntrack_expect *
ctnetlink_alloc_expect(const struct nlattr *const cda[], struct nf_conn *ct,
+ const struct nf_conntrack_helper *assign_helper,
struct nf_conntrack_tuple *tuple,
struct nf_conntrack_tuple *mask);
@@ -2860,6 +2861,7 @@ static int
ctnetlink_glue_attach_expect(const struct nlattr *attr, struct nf_conn *ct,
u32 portid, u32 report)
{
+ struct nf_conntrack_helper *assign_helper = NULL;
struct nlattr *cda[CTA_EXPECT_MAX+1];
struct nf_conntrack_tuple tuple, mask;
struct nf_conntrack_expect *exp;
@@ -2870,13 +2872,26 @@ ctnetlink_glue_attach_expect(const struct nlattr *attr, struct nf_conn *ct,
if (err < 0)
return err;
+ if (!cda[CTA_EXPECT_TUPLE] || !cda[CTA_EXPECT_MASK])
+ return -EINVAL;
+
err = ctnetlink_glue_exp_parse((const struct nlattr * const *)cda,
ct, &tuple, &mask);
if (err < 0)
return err;
+ if (cda[CTA_EXPECT_HELP_NAME]) {
+ const char *helpname = nla_data(cda[CTA_EXPECT_HELP_NAME]);
+
+ assign_helper = __nf_conntrack_helper_find(helpname,
+ nf_ct_l3num(ct),
+ tuple.dst.protonum);
+ if (!assign_helper)
+ return -EOPNOTSUPP;
+ }
+
exp = ctnetlink_alloc_expect((const struct nlattr * const *)cda, ct,
- &tuple, &mask);
+ assign_helper, &tuple, &mask);
if (IS_ERR(exp))
return PTR_ERR(exp);
@@ -3515,6 +3530,7 @@ ctnetlink_parse_expect_nat(const struct nlattr *attr,
static struct nf_conntrack_expect *
ctnetlink_alloc_expect(const struct nlattr * const cda[], struct nf_conn *ct,
+ const struct nf_conntrack_helper *assign_helper,
struct nf_conntrack_tuple *tuple,
struct nf_conntrack_tuple *mask)
{
@@ -3568,6 +3584,7 @@ ctnetlink_alloc_expect(const struct nlattr * const cda[], struct nf_conn *ct,
exp->zone = ct->zone;
#endif
rcu_assign_pointer(exp->helper, helper);
+ rcu_assign_pointer(exp->assign_helper, assign_helper);
exp->tuple = *tuple;
exp->mask.src.u3 = mask->src.u3;
exp->mask.src.u.all = mask->src.u.all;
@@ -3623,7 +3640,7 @@ ctnetlink_create_expect(struct net *net,
ct = nf_ct_tuplehash_to_ctrack(h);
rcu_read_lock();
- exp = ctnetlink_alloc_expect(cda, ct, &tuple, &mask);
+ exp = ctnetlink_alloc_expect(cda, ct, NULL, &tuple, &mask);
if (IS_ERR(exp)) {
err = PTR_ERR(exp);
goto err_rcu;
diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c
index 1eb55907d470..e69941f1a101 100644
--- a/net/netfilter/nf_conntrack_sip.c
+++ b/net/netfilter/nf_conntrack_sip.c
@@ -1366,6 +1366,10 @@ static int process_register_request(struct sk_buff *skb, unsigned int protoff,
goto store_cseq;
}
+ helper = rcu_dereference(nfct_help(ct)->helper);
+ if (!helper)
+ return NF_DROP;
+
exp = nf_ct_expect_alloc(ct);
if (!exp) {
nf_ct_helper_log(skb, ct, "cannot alloc expectation");
@@ -1376,14 +1380,10 @@ static int process_register_request(struct sk_buff *skb, unsigned int protoff,
if (sip_direct_signalling)
saddr = &ct->tuplehash[!dir].tuple.src.u3;
- helper = rcu_dereference(nfct_help(ct)->helper);
- if (!helper)
- return NF_DROP;
-
nf_ct_expect_init(exp, SIP_EXPECT_SIGNALLING, nf_ct_l3num(ct),
saddr, &daddr, proto, NULL, &port);
exp->timeout.expires = sip_timeout * HZ;
- rcu_assign_pointer(exp->helper, helper);
+ rcu_assign_pointer(exp->assign_helper, helper);
exp->flags = NF_CT_EXPECT_PERMANENT | NF_CT_EXPECT_INACTIVE;
hooks = rcu_dereference(nf_nat_sip_hooks);
diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c
index 60ee8d932fcb..fa2cc556331c 100644
--- a/net/netfilter/nft_ct.c
+++ b/net/netfilter/nft_ct.c
@@ -1334,6 +1334,8 @@ static void nft_ct_expect_obj_eval(struct nft_object *obj,
if (nf_ct_expect_related(exp, 0) != 0)
regs->verdict.code = NF_DROP;
+
+ nf_ct_expect_put(exp);
}
static const struct nla_policy nft_ct_expect_policy[NFTA_CT_EXPECT_MAX + 1] = {
diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index 2c67c2e6b132..4e6708c23922 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -55,6 +55,9 @@ static struct list_head xt_templates[NFPROTO_NUMPROTO];
struct xt_pernet {
struct list_head tables[NFPROTO_NUMPROTO];
+
+ /* stash area used during netns exit */
+ struct list_head dead_tables[NFPROTO_NUMPROTO];
};
struct compat_delta {
@@ -1472,11 +1475,9 @@ struct xt_counters *xt_counters_alloc(unsigned int counters)
}
EXPORT_SYMBOL(xt_counters_alloc);
-struct xt_table_info *
-xt_replace_table(struct xt_table *table,
- unsigned int num_counters,
- struct xt_table_info *newinfo,
- int *error)
+static struct xt_table_info *
+do_replace_table(struct xt_table *table, unsigned int num_counters,
+ struct xt_table_info *newinfo, int *error)
{
struct xt_table_info *private;
unsigned int cpu;
@@ -1531,30 +1532,54 @@ xt_replace_table(struct xt_table *table,
}
}
- audit_log_nfcfg(table->name, table->af, private->number,
- !private->number ? AUDIT_XT_OP_REGISTER :
- AUDIT_XT_OP_REPLACE,
- GFP_KERNEL);
+ return private;
+}
+
+struct xt_table_info *
+xt_replace_table(struct xt_table *table, unsigned int num_counters,
+ struct xt_table_info *newinfo,
+ int *error)
+{
+ struct xt_table_info *private;
+
+ private = do_replace_table(table, num_counters, newinfo, error);
+ if (private)
+ audit_log_nfcfg(table->name, table->af, private->number,
+ AUDIT_XT_OP_REPLACE,
+ GFP_KERNEL);
+
return private;
}
EXPORT_SYMBOL_GPL(xt_replace_table);
struct xt_table *xt_register_table(struct net *net,
const struct xt_table *input_table,
+ const struct nf_hook_ops *template_ops,
struct xt_table_info *bootstrap,
struct xt_table_info *newinfo)
{
struct xt_pernet *xt_net = net_generic(net, xt_pernet_id);
+ struct xt_table *t, *table = NULL;
+ struct nf_hook_ops *ops = NULL;
struct xt_table_info *private;
- struct xt_table *t, *table;
- int ret;
+ unsigned int num_ops;
+ int ret = -EINVAL;
+
+ num_ops = hweight32(input_table->valid_hooks);
+ if (num_ops == 0)
+ goto out;
+
+ ret = -ENOMEM;
+ if (template_ops) {
+ ops = kmemdup_array(template_ops, num_ops, sizeof(*ops), GFP_KERNEL);
+ if (!ops)
+ goto out;
+ }
/* Don't add one object to multiple lists. */
table = kmemdup(input_table, sizeof(struct xt_table), GFP_KERNEL);
- if (!table) {
- ret = -ENOMEM;
+ if (!table)
goto out;
- }
mutex_lock(&xt[table->af].mutex);
/* Don't autoload: we'd eat our tail... */
@@ -1568,7 +1593,7 @@ struct xt_table *xt_register_table(struct net *net,
/* Simplifies replace_table code. */
table->private = bootstrap;
- if (!xt_replace_table(table, 0, newinfo, &ret))
+ if (!do_replace_table(table, 0, newinfo, &ret))
goto unlock;
private = table->private;
@@ -1577,34 +1602,122 @@ struct xt_table *xt_register_table(struct net *net,
/* save number of initial entries */
private->initial_entries = private->number;
+ if (ops) {
+ int i;
+
+ for (i = 0; i < num_ops; i++)
+ ops[i].priv = table;
+
+ ret = nf_register_net_hooks(net, ops, num_ops);
+ if (ret != 0) {
+ mutex_unlock(&xt[table->af].mutex);
+ /* nf_register_net_hooks() might have published a
+ * base chain before internal error unwind.
+ */
+ synchronize_rcu();
+ goto out;
+ }
+
+ table->ops = ops;
+ }
+
+ audit_log_nfcfg(table->name, table->af, private->number,
+ AUDIT_XT_OP_REGISTER, GFP_KERNEL);
+
list_add(&table->list, &xt_net->tables[table->af]);
mutex_unlock(&xt[table->af].mutex);
return table;
unlock:
mutex_unlock(&xt[table->af].mutex);
- kfree(table);
out:
+ kfree(table);
+ kfree(ops);
return ERR_PTR(ret);
}
EXPORT_SYMBOL_GPL(xt_register_table);
-void *xt_unregister_table(struct xt_table *table)
+/**
+ * xt_unregister_table_pre_exit - pre-shutdown unregister of a table
+ * @net: network namespace
+ * @af: address family (e.g., NFPROTO_IPV4, NFPROTO_IPV6)
+ * @name: name of the table to unregister
+ *
+ * Unregisters the specified netfilter table from the given network namespace
+ * and also unregisters the hooks from netfilter core: no new packets will be
+ * processed.
+ *
+ * This must be called prior to xt_unregister_table_exit() from the pernet
+ * .pre_exit callback. After this call, the table is no longer visible to
+ * the get/setsockopt path. In case of rmmod, module exit path must have
+ * called xt_unregister_template() prior to unregistering pernet ops to
+ * prevent re-instantiation of the table.
+ *
+ * See also: xt_unregister_table_exit()
+ */
+void xt_unregister_table_pre_exit(struct net *net, u8 af, const char *name)
{
- struct xt_table_info *private;
+ struct xt_pernet *xt_net = net_generic(net, xt_pernet_id);
+ struct xt_table *t;
- mutex_lock(&xt[table->af].mutex);
- private = table->private;
- list_del(&table->list);
- mutex_unlock(&xt[table->af].mutex);
- audit_log_nfcfg(table->name, table->af, private->number,
- AUDIT_XT_OP_UNREGISTER, GFP_KERNEL);
- kfree(table->ops);
- kfree(table);
+ mutex_lock(&xt[af].mutex);
+ list_for_each_entry(t, &xt_net->tables[af], list) {
+ if (strcmp(t->name, name) == 0) {
+ list_move(&t->list, &xt_net->dead_tables[af]);
+ mutex_unlock(&xt[af].mutex);
- return private;
+ if (t->ops) /* nat table registers with nat core, t->ops is NULL. */
+ nf_unregister_net_hooks(net, t->ops, hweight32(t->valid_hooks));
+ return;
+ }
+ }
+ mutex_unlock(&xt[af].mutex);
+}
+EXPORT_SYMBOL(xt_unregister_table_pre_exit);
+
+/**
+ * xt_unregister_table_exit - remove a table during namespace teardown
+ * @net: the network namespace from which to unregister the table
+ * @af: address family (e.g., NFPROTO_IPV4, NFPROTO_IPV6)
+ * @name: name of the table to unregister
+ *
+ * Completes the unregister process for a table. This must be called from
+ * the pernet ops .exit callback. This is the second stage after
+ * xt_unregister_table_pre_exit().
+ *
+ * pair with xt_unregister_table_pre_exit() during namespace shutdown.
+ *
+ * Return: the unregistered table or NULL if the table was never
+ * instantiated. The caller needs to kfree() the table after it
+ * has removed the family specific matches/targets.
+ */
+struct xt_table *xt_unregister_table_exit(struct net *net, u8 af, const char *name)
+{
+ struct xt_pernet *xt_net = net_generic(net, xt_pernet_id);
+ struct xt_table *table;
+
+ mutex_lock(&xt[af].mutex);
+ list_for_each_entry(table, &xt_net->dead_tables[af], list) {
+ struct nf_hook_ops *ops = NULL;
+
+ if (strcmp(table->name, name) != 0)
+ continue;
+
+ list_del(&table->list);
+
+ audit_log_nfcfg(table->name, table->af, table->private->number,
+ AUDIT_XT_OP_UNREGISTER, GFP_KERNEL);
+ swap(table->ops, ops);
+ mutex_unlock(&xt[af].mutex);
+
+ kfree(ops);
+ return table;
+ }
+ mutex_unlock(&xt[af].mutex);
+
+ return NULL;
}
-EXPORT_SYMBOL_GPL(xt_unregister_table);
+EXPORT_SYMBOL_GPL(xt_unregister_table_exit);
#endif
#ifdef CONFIG_PROC_FS
@@ -2051,8 +2164,10 @@ static int __net_init xt_net_init(struct net *net)
struct xt_pernet *xt_net = net_generic(net, xt_pernet_id);
int i;
- for (i = 0; i < NFPROTO_NUMPROTO; i++)
+ for (i = 0; i < NFPROTO_NUMPROTO; i++) {
INIT_LIST_HEAD(&xt_net->tables[i]);
+ INIT_LIST_HEAD(&xt_net->dead_tables[i]);
+ }
return 0;
}
@@ -2061,8 +2176,10 @@ static void __net_exit xt_net_exit(struct net *net)
struct xt_pernet *xt_net = net_generic(net, xt_pernet_id);
int i;
- for (i = 0; i < NFPROTO_NUMPROTO; i++)
+ for (i = 0; i < NFPROTO_NUMPROTO; i++) {
WARN_ON_ONCE(!list_empty(&xt_net->tables[i]));
+ WARN_ON_ONCE(!list_empty(&xt_net->dead_tables[i]));
+ }
}
static struct pernet_operations xt_net_ops = {
diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index d251d894afd4..0da39eaed255 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -1972,8 +1972,10 @@ int genlmsg_multicast_allns(const struct genl_family *family,
struct sk_buff *skb, u32 portid,
unsigned int group)
{
- if (WARN_ON_ONCE(group >= family->n_mcgrps))
+ if (WARN_ON_ONCE(group >= family->n_mcgrps)) {
+ kfree_skb(skb);
return -EINVAL;
+ }
group = family->mcgrp_offset + group;
return genlmsg_mcast(skb, portid, group);
@@ -1986,8 +1988,10 @@ void genl_notify(const struct genl_family *family, struct sk_buff *skb,
struct net *net = genl_info_net(info);
struct sock *sk = net->genl_sock;
- if (WARN_ON_ONCE(group >= family->n_mcgrps))
+ if (WARN_ON_ONCE(group >= family->n_mcgrps)) {
+ kfree_skb(skb);
return;
+ }
group = family->mcgrp_offset + group;
nlmsg_notify(sk, skb, info->snd_portid, group,
diff --git a/net/rds/message.c b/net/rds/message.c
index 25fedcb3cd00..7feb0eb6537d 100644
--- a/net/rds/message.c
+++ b/net/rds/message.c
@@ -448,6 +448,7 @@ static int rds_message_zcopy_from_user(struct rds_message *rm, struct iov_iter *
for (i = 0; i < rm->data.op_nents; i++)
put_page(sg_page(&rm->data.op_sg[i]));
+ rm->data.op_nents = 0;
mmp = &rm->data.op_mmp_znotifier->z_mmp;
mm_unaccount_pinned_pages(mmp);
ret = -EFAULT;
diff --git a/net/sched/sch_cbs.c b/net/sched/sch_cbs.c
index 8c9a0400c862..0f953bd46b58 100644
--- a/net/sched/sch_cbs.c
+++ b/net/sched/sch_cbs.c
@@ -243,6 +243,20 @@ static struct sk_buff *cbs_dequeue(struct Qdisc *sch)
return q->dequeue(sch);
}
+static void cbs_reset(struct Qdisc *sch)
+{
+ struct cbs_sched_data *q = qdisc_priv(sch);
+
+ /* Nothing to do if we couldn't create the underlying qdisc */
+ if (!q->qdisc)
+ return;
+
+ qdisc_reset(q->qdisc);
+ qdisc_watchdog_cancel(&q->watchdog);
+ q->credits = 0;
+ q->last = 0;
+}
+
static const struct nla_policy cbs_policy[TCA_CBS_MAX + 1] = {
[TCA_CBS_PARMS] = { .len = sizeof(struct tc_cbs_qopt) },
};
@@ -540,7 +554,7 @@ static struct Qdisc_ops cbs_qdisc_ops __read_mostly = {
.dequeue = cbs_dequeue,
.peek = qdisc_peek_dequeued,
.init = cbs_init,
- .reset = qdisc_reset_queue,
+ .reset = cbs_reset,
.destroy = cbs_destroy,
.change = cbs_change,
.dump = cbs_dump,
diff --git a/net/sched/sch_dualpi2.c b/net/sched/sch_dualpi2.c
index 241e6a46bd00..a22489c14458 100644
--- a/net/sched/sch_dualpi2.c
+++ b/net/sched/sch_dualpi2.c
@@ -938,6 +938,8 @@ static int dualpi2_init(struct Qdisc *sch, struct nlattr *opt,
int err;
sch->flags |= TCQ_F_DEQUEUE_DROPS;
+ hrtimer_setup(&q->pi2_timer, dualpi2_timer, CLOCK_MONOTONIC,
+ HRTIMER_MODE_ABS_PINNED_SOFT);
q->l_queue = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops,
TC_H_MAKE(sch->handle, 1), extack);
@@ -950,8 +952,6 @@ static int dualpi2_init(struct Qdisc *sch, struct nlattr *opt,
q->sch = sch;
dualpi2_reset_default(sch);
- hrtimer_setup(&q->pi2_timer, dualpi2_timer, CLOCK_MONOTONIC,
- HRTIMER_MODE_ABS_PINNED_SOFT);
if (opt && nla_len(opt)) {
err = dualpi2_change(sch, opt, extack);
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 58d0d9747f0b..1d2568bb6bc2 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -1986,6 +1986,15 @@ static int sctp_sendmsg(struct sock *sk, struct msghdr *msg, size_t msg_len)
goto out_unlock;
iov_iter_revert(&msg->msg_iter, err);
+
+ /* sctp_sendmsg_to_asoc() may have released the socket
+ * lock (sctp_wait_for_sndbuf), during which other
+ * associations on ep->asocs could have been peeled
+ * off or freed. @asoc itself is revalidated by the
+ * base.dead and base.sk checks in sctp_wait_for_sndbuf,
+ * so re-derive the cached cursor from it.
+ */
+ tmp = list_next_entry(asoc, asocs);
}
goto out_unlock;
diff --git a/net/shaper/shaper.c b/net/shaper/shaper.c
index 94bc9c7382ea..b1c65110f04d 100644
--- a/net/shaper/shaper.c
+++ b/net/shaper/shaper.c
@@ -21,6 +21,8 @@
#define NET_SHAPER_ID_UNSPEC NET_SHAPER_ID_MASK
+static_assert(NET_SHAPER_ID_UNSPEC == NET_SHAPER_MAX_HANDLE_ID + 1);
+
struct net_shaper_hierarchy {
struct xarray shapers;
};
@@ -90,6 +92,12 @@ static int net_shaper_handle_size(void)
nla_total_size(sizeof(u32)));
}
+static int net_shaper_group_reply_size(void)
+{
+ return nla_total_size(sizeof(u32)) + /* NET_SHAPER_A_IFINDEX */
+ net_shaper_handle_size(); /* NET_SHAPER_A_HANDLE */
+}
+
static int net_shaper_fill_binding(struct sk_buff *msg,
const struct net_shaper_binding *binding,
u32 type)
@@ -275,11 +283,13 @@ static void net_shaper_default_parent(const struct net_shaper_handle *handle,
parent->id = 0;
}
-/*
- * MARK_0 is already in use due to XA_FLAGS_ALLOC, can't reuse such flag as
- * it's cleared by xa_store().
+/* MARK_0 is already in use due to XA_FLAGS_ALLOC. The VALID mark is set on
+ * an entry only after the device-side configuration has completed
+ * successfully (see net_shaper_commit()). Lookups and dumps must filter on
+ * this mark to avoid exposing tentative entries inserted by
+ * net_shaper_pre_insert() while the driver call is still in flight.
*/
-#define NET_SHAPER_NOT_VALID XA_MARK_1
+#define NET_SHAPER_VALID XA_MARK_1
static struct net_shaper *
net_shaper_lookup(struct net_shaper_binding *binding,
@@ -289,10 +299,14 @@ net_shaper_lookup(struct net_shaper_binding *binding,
struct net_shaper_hierarchy *hierarchy;
hierarchy = net_shaper_hierarchy_rcu(binding);
- if (!hierarchy || xa_get_mark(&hierarchy->shapers, index,
- NET_SHAPER_NOT_VALID))
+ if (!hierarchy || !xa_get_mark(&hierarchy->shapers, index,
+ NET_SHAPER_VALID))
return NULL;
+ /* Pairs with smp_wmb() in net_shaper_commit(): if the entry is
+ * valid, its contents must be visible too.
+ */
+ smp_rmb();
return xa_load(&hierarchy->shapers, index);
}
@@ -348,7 +362,7 @@ static int net_shaper_pre_insert(struct net_shaper_binding *binding,
handle->id == NET_SHAPER_ID_UNSPEC) {
u32 min, max;
- handle->id = NET_SHAPER_ID_MASK - 1;
+ handle->id = NET_SHAPER_MAX_HANDLE_ID;
max = net_shaper_handle_to_index(handle);
handle->id = 0;
min = net_shaper_handle_to_index(handle);
@@ -370,13 +384,10 @@ static int net_shaper_pre_insert(struct net_shaper_binding *binding,
goto free_id;
}
- /* Mark 'tentative' shaper inside the hierarchy container.
- * xa_set_mark is a no-op if the previous store fails.
+ /* Insert as 'tentative' (no VALID mark). The mark will be set by
+ * net_shaper_commit() once the driver-side configuration succeeds.
*/
- xa_lock(&hierarchy->shapers);
- prev = __xa_store(&hierarchy->shapers, index, cur, GFP_KERNEL);
- __xa_set_mark(&hierarchy->shapers, index, NET_SHAPER_NOT_VALID);
- xa_unlock(&hierarchy->shapers);
+ prev = xa_store(&hierarchy->shapers, index, cur, GFP_KERNEL);
if (xa_err(prev)) {
NL_SET_ERR_MSG(extack, "Can't insert shaper into device store");
kfree_rcu(cur, rcu);
@@ -413,9 +424,9 @@ static void net_shaper_commit(struct net_shaper_binding *binding,
/* Successful update: drop the tentative mark
* and update the hierarchy container.
*/
- __xa_clear_mark(&hierarchy->shapers, index,
- NET_SHAPER_NOT_VALID);
*cur = shapers[i];
+ smp_wmb();
+ __xa_set_mark(&hierarchy->shapers, index, NET_SHAPER_VALID);
}
xa_unlock(&hierarchy->shapers);
}
@@ -431,8 +442,9 @@ static void net_shaper_rollback(struct net_shaper_binding *binding)
return;
xa_lock(&hierarchy->shapers);
- xa_for_each_marked(&hierarchy->shapers, index, cur,
- NET_SHAPER_NOT_VALID) {
+ xa_for_each(&hierarchy->shapers, index, cur) {
+ if (xa_get_mark(&hierarchy->shapers, index, NET_SHAPER_VALID))
+ continue;
__xa_erase(&hierarchy->shapers, index);
kfree(cur);
}
@@ -465,10 +477,21 @@ static int net_shaper_parse_handle(const struct nlattr *attr,
* shaper (any other value).
*/
id_attr = tb[NET_SHAPER_A_HANDLE_ID];
- if (id_attr)
+ if (id_attr) {
id = nla_get_u32(id_attr);
- else if (handle->scope == NET_SHAPER_SCOPE_NODE)
+ } else if (handle->scope == NET_SHAPER_SCOPE_NODE) {
id = NET_SHAPER_ID_UNSPEC;
+ } else if (handle->scope == NET_SHAPER_SCOPE_QUEUE) {
+ NL_SET_ERR_ATTR_MISS(info->extack, attr,
+ NET_SHAPER_A_HANDLE_ID);
+ return -EINVAL;
+ }
+
+ if (id && handle->scope == NET_SHAPER_SCOPE_NETDEV) {
+ NL_SET_ERR_MSG_ATTR(info->extack, id_attr,
+ "Netdev scope is a singleton, must use ID 0");
+ return -EINVAL;
+ }
handle->id = id;
return 0;
@@ -836,7 +859,12 @@ int net_shaper_nl_get_dumpit(struct sk_buff *skb,
goto out_unlock;
for (; (shaper = xa_find(&hierarchy->shapers, &ctx->start_index,
- U32_MAX, XA_PRESENT)); ctx->start_index++) {
+ U32_MAX, NET_SHAPER_VALID));
+ ctx->start_index++) {
+ /* Pairs with smp_wmb() in net_shaper_commit(): the entry
+ * is marked VALID, so its contents must be visible too.
+ */
+ smp_rmb();
ret = net_shaper_fill_one(skb, binding, shaper, info);
if (ret)
break;
@@ -932,6 +960,46 @@ static int net_shaper_handle_cmp(const struct net_shaper_handle *a,
return memcmp(a, b, sizeof(*a));
}
+static int net_shaper_parse_leaves(struct net_shaper_binding *binding,
+ struct genl_info *info,
+ const struct net_shaper *node,
+ struct net_shaper *leaves,
+ int leaves_count)
+{
+ struct nlattr *attr;
+ int i, j, ret, rem;
+
+ i = 0;
+ nla_for_each_attr_type(attr, NET_SHAPER_A_LEAVES,
+ genlmsg_data(info->genlhdr),
+ genlmsg_len(info->genlhdr), rem) {
+ if (WARN_ON_ONCE(i >= leaves_count))
+ return -EINVAL;
+
+ ret = net_shaper_parse_leaf(binding, attr, info,
+ node, &leaves[i]);
+ if (ret)
+ return ret;
+
+ /* Reject duplicates */
+ for (j = 0; j < i; j++) {
+ if (net_shaper_handle_cmp(&leaves[i].handle,
+ &leaves[j].handle))
+ continue;
+
+ NL_SET_ERR_MSG_ATTR_FMT(info->extack, attr,
+ "Duplicate leaf shaper %d:%d",
+ leaves[i].handle.scope,
+ leaves[i].handle.id);
+ return -EINVAL;
+ }
+
+ i++;
+ }
+
+ return 0;
+}
+
static int net_shaper_parent_from_leaves(int leaves_count,
const struct net_shaper *leaves,
struct net_shaper *node,
@@ -964,15 +1032,22 @@ static int __net_shaper_group(struct net_shaper_binding *binding,
int i, ret;
if (node->handle.scope == NET_SHAPER_SCOPE_NODE) {
+ struct net_shaper *cur = NULL;
+
new_node = node->handle.id == NET_SHAPER_ID_UNSPEC;
- if (!new_node && !net_shaper_lookup(binding, &node->handle)) {
- /* The related attribute is not available when
- * reaching here from the delete() op.
- */
- NL_SET_ERR_MSG_FMT(extack, "Node shaper %d:%d does not exists",
- node->handle.scope, node->handle.id);
- return -ENOENT;
+ if (!new_node) {
+ cur = net_shaper_lookup(binding, &node->handle);
+ if (!cur) {
+ /* The related attribute is not available
+ * when reaching here from the delete() op.
+ */
+ NL_SET_ERR_MSG_FMT(extack,
+ "Node shaper %d:%d does not exist",
+ node->handle.scope,
+ node->handle.id);
+ return -ENOENT;
+ }
}
/* When unspecified, the node parent scope is inherited from
@@ -986,6 +1061,15 @@ static int __net_shaper_group(struct net_shaper_binding *binding,
return ret;
}
+ if (cur && net_shaper_handle_cmp(&cur->parent,
+ &node->parent)) {
+ NL_SET_ERR_MSG_FMT(extack,
+ "Cannot reparent node shaper %d:%d",
+ node->handle.scope,
+ node->handle.id);
+ return -EOPNOTSUPP;
+ }
+
} else {
net_shaper_default_parent(&node->handle, &node->parent);
}
@@ -1162,7 +1246,7 @@ static int net_shaper_group_send_reply(struct net_shaper_binding *binding,
free_msg:
/* Should never happen as msg is pre-allocated with enough space. */
WARN_ONCE(true, "calculated message payload length (%d)",
- net_shaper_handle_size());
+ net_shaper_group_reply_size());
nlmsg_free(msg);
return -EMSGSIZE;
}
@@ -1172,10 +1256,9 @@ int net_shaper_nl_group_doit(struct sk_buff *skb, struct genl_info *info)
struct net_shaper **old_nodes, *leaves, node = {};
struct net_shaper_hierarchy *hierarchy;
struct net_shaper_binding *binding;
- int i, ret, rem, leaves_count;
+ int i, ret, leaves_count;
int old_nodes_count = 0;
struct sk_buff *msg;
- struct nlattr *attr;
if (GENL_REQ_ATTR_CHECK(info, NET_SHAPER_A_LEAVES))
return -EINVAL;
@@ -1203,26 +1286,19 @@ int net_shaper_nl_group_doit(struct sk_buff *skb, struct genl_info *info)
if (ret)
goto free_leaves;
- i = 0;
- nla_for_each_attr_type(attr, NET_SHAPER_A_LEAVES,
- genlmsg_data(info->genlhdr),
- genlmsg_len(info->genlhdr), rem) {
- if (WARN_ON_ONCE(i >= leaves_count))
- goto free_leaves;
-
- ret = net_shaper_parse_leaf(binding, attr, info,
- &node, &leaves[i]);
- if (ret)
- goto free_leaves;
- i++;
- }
+ ret = net_shaper_parse_leaves(binding, info, &node,
+ leaves, leaves_count);
+ if (ret)
+ goto free_leaves;
/* Prepare the msg reply in advance, to avoid device operation
* rollback on allocation failure.
*/
- msg = genlmsg_new(net_shaper_handle_size(), GFP_KERNEL);
- if (!msg)
+ msg = genlmsg_new(net_shaper_group_reply_size(), GFP_KERNEL);
+ if (!msg) {
+ ret = -ENOMEM;
goto free_leaves;
+ }
hierarchy = net_shaper_hierarchy_setup(binding);
if (!hierarchy) {
diff --git a/net/shaper/shaper_nl_gen.c b/net/shaper/shaper_nl_gen.c
index 9b29be3ef19a..76eff85ec66d 100644
--- a/net/shaper/shaper_nl_gen.c
+++ b/net/shaper/shaper_nl_gen.c
@@ -11,10 +11,15 @@
#include <uapi/linux/net_shaper.h>
+/* Integer value ranges */
+static const struct netlink_range_validation net_shaper_a_handle_id_range = {
+ .max = NET_SHAPER_MAX_HANDLE_ID,
+};
+
/* Common nested types */
const struct nla_policy net_shaper_handle_nl_policy[NET_SHAPER_A_HANDLE_ID + 1] = {
[NET_SHAPER_A_HANDLE_SCOPE] = NLA_POLICY_MAX(NLA_U32, 3),
- [NET_SHAPER_A_HANDLE_ID] = { .type = NLA_U32, },
+ [NET_SHAPER_A_HANDLE_ID] = NLA_POLICY_FULL_RANGE(NLA_U32, &net_shaper_a_handle_id_range),
};
const struct nla_policy net_shaper_leaf_info_nl_policy[NET_SHAPER_A_WEIGHT + 1] = {
diff --git a/net/shaper/shaper_nl_gen.h b/net/shaper/shaper_nl_gen.h
index 42c46c52c775..2406652a9014 100644
--- a/net/shaper/shaper_nl_gen.h
+++ b/net/shaper/shaper_nl_gen.h
@@ -12,6 +12,8 @@
#include <uapi/linux/net_shaper.h>
+#define NET_SHAPER_MAX_HANDLE_ID 67108862
+
/* Common nested types */
extern const struct nla_policy net_shaper_handle_nl_policy[NET_SHAPER_A_HANDLE_ID + 1];
extern const struct nla_policy net_shaper_leaf_info_nl_policy[NET_SHAPER_A_WEIGHT + 1];
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 185dbed7de5d..dffbd529762d 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -1400,7 +1400,8 @@ smc_v2_determine_accepted_chid(struct smc_clc_msg_accept_confirm *aclc,
int i;
for (i = 0; i < ini->ism_offered_cnt + 1; i++) {
- if (ini->ism_chid[i] == ntohs(aclc->d1.chid)) {
+ if (ini->ism_dev[i] &&
+ ini->ism_chid[i] == ntohs(aclc->d1.chid)) {
ini->ism_selected = i;
return 0;
}
@@ -3054,18 +3055,17 @@ static int __smc_setsockopt(struct socket *sock, int level, int optname,
smc = smc_sk(sk);
+ /* pre-fetch user data outside the lock */
+ if (optname == SMC_LIMIT_HS) {
+ if (optlen < sizeof(int))
+ return -EINVAL;
+ if (copy_from_sockptr(&val, optval, sizeof(int)))
+ return -EFAULT;
+ }
+
lock_sock(sk);
switch (optname) {
case SMC_LIMIT_HS:
- if (optlen < sizeof(int)) {
- rc = -EINVAL;
- break;
- }
- if (copy_from_sockptr(&val, optval, sizeof(int))) {
- rc = -EFAULT;
- break;
- }
-
smc->limit_smc_hs = !!val;
rc = 0;
break;
diff --git a/net/smc/smc_tracepoint.h b/net/smc/smc_tracepoint.h
index a9a6e3c1113a..53da84f57fd6 100644
--- a/net/smc/smc_tracepoint.h
+++ b/net/smc/smc_tracepoint.h
@@ -51,7 +51,7 @@ DECLARE_EVENT_CLASS(smc_msg_event,
__field(const void *, smc)
__field(u64, net_cookie)
__field(size_t, len)
- __string(name, smc->conn.lnk->ibname)
+ __string(name, smc->conn.lnk ? smc->conn.lnk->ibname : "")
),
TP_fast_assign(
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 2590e855f6a5..3bfdaf5e64f5 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -789,23 +789,33 @@ static int tls_push_record(struct sock *sk, int flags,
i = msg_pl->sg.end;
sk_msg_iter_var_prev(i);
+ /* msg_pl->sg.data is a ring; data[MAX+1] is reserved for the wrap
+ * link (frags won't use it). 'i' is now the last filled entry:
+ *
+ * i end start
+ * v v v [ rsv ]
+ * [ d ][ d ][ ][ ]...[ ][ d ][ d ][ d ][chain]
+ * ^ END v
+ * `-----------------------------------------'
+ *
+ * Note that SGL does not allow chain-after-chain, so for TLS 1.3,
+ * we must make sure we don't create the wrap entry and then chain
+ * link to content_type immediately at index 0.
+ */
+ if (i < msg_pl->sg.start)
+ sg_chain(msg_pl->sg.data, ARRAY_SIZE(msg_pl->sg.data),
+ msg_pl->sg.data);
+
rec->content_type = record_type;
if (prot->version == TLS_1_3_VERSION) {
/* Add content type to end of message. No padding added */
sg_set_buf(&rec->sg_content_type, &rec->content_type, 1);
sg_mark_end(&rec->sg_content_type);
- sg_chain(msg_pl->sg.data, msg_pl->sg.end + 1,
- &rec->sg_content_type);
+ sg_chain(msg_pl->sg.data, i + 2, &rec->sg_content_type);
} else {
sg_mark_end(sk_msg_elem(msg_pl, i));
}
- if (msg_pl->sg.end < msg_pl->sg.start) {
- sg_chain(&msg_pl->sg.data[msg_pl->sg.start],
- MAX_SKB_FRAGS - msg_pl->sg.start + 1,
- msg_pl->sg.data);
- }
-
i = msg_pl->sg.start;
sg_chain(rec->sg_aead_in, 2, &msg_pl->sg.data[i]);
diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
index 9b8014516f4f..989cc252d3d3 100644
--- a/net/vmw_vsock/virtio_transport_common.c
+++ b/net/vmw_vsock/virtio_transport_common.c
@@ -136,27 +136,6 @@ static void virtio_transport_init_hdr(struct sk_buff *skb,
hdr->fwd_cnt = cpu_to_le32(0);
}
-static void virtio_transport_copy_nonlinear_skb(const struct sk_buff *skb,
- void *dst,
- size_t len)
-{
- struct iov_iter iov_iter = { 0 };
- struct kvec kvec;
- size_t to_copy;
-
- kvec.iov_base = dst;
- kvec.iov_len = len;
-
- iov_iter.iter_type = ITER_KVEC;
- iov_iter.kvec = &kvec;
- iov_iter.nr_segs = 1;
-
- to_copy = min_t(size_t, len, skb->len);
-
- skb_copy_datagram_iter(skb, VIRTIO_VSOCK_SKB_CB(skb)->offset,
- &iov_iter, to_copy);
-}
-
/* Packet capture */
static struct sk_buff *virtio_transport_build_skb(void *opaque)
{
@@ -166,12 +145,12 @@ static struct sk_buff *virtio_transport_build_skb(void *opaque)
struct sk_buff *skb;
size_t payload_len;
- /* A packet could be split to fit the RX buffer, so we can retrieve
- * the payload length from the header and the buffer pointer taking
- * care of the offset in the original packet.
+ /* A packet could be split to fit the RX buffer, so we use
+ * the payload length from the header, which has been updated
+ * by the sender to reflect the fragment size.
*/
pkt_hdr = virtio_vsock_hdr(pkt);
- payload_len = pkt->len;
+ payload_len = le32_to_cpu(pkt_hdr->len);
skb = alloc_skb(sizeof(*hdr) + sizeof(*pkt_hdr) + payload_len,
GFP_ATOMIC);
@@ -214,12 +193,18 @@ static struct sk_buff *virtio_transport_build_skb(void *opaque)
skb_put_data(skb, pkt_hdr, sizeof(*pkt_hdr));
if (payload_len) {
- if (skb_is_nonlinear(pkt)) {
- void *data = skb_put(skb, payload_len);
-
- virtio_transport_copy_nonlinear_skb(pkt, data, payload_len);
- } else {
- skb_put_data(skb, pkt->data, payload_len);
+ struct iov_iter iov_iter;
+ struct kvec kvec;
+ void *data = skb_put(skb, payload_len);
+
+ kvec.iov_base = data;
+ kvec.iov_len = payload_len;
+ iov_iter_kvec(&iov_iter, ITER_DEST, &kvec, 1, payload_len);
+
+ if (skb_copy_datagram_iter(pkt, VIRTIO_VSOCK_SKB_CB(pkt)->offset,
+ &iov_iter, payload_len)) {
+ kfree_skb(skb);
+ return NULL;
}
}