aboutsummaryrefslogtreecommitdiff
path: root/net
diff options
context:
space:
mode:
authorAlexei Starovoitov2024-08-22 09:27:59 -0700
committerAlexei Starovoitov2024-08-22 09:48:44 -0700
commit50c374c6d1a43db9444cb74cc09552c817db2a9b (patch)
treeb80c7befe92ef07799cf2dca3135afe56a6a646f /net
parentd352eca2662734cdd5ef90df1f8bc28b9505e36f (diff)
parent872cf28b8df9c5c3a1e71a88ee750df7c2513971 (diff)
Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf
Cross-merge bpf fixes after downstream PR including important fixes (from bpf-next point of view): commit 41c24102af7b ("selftests/bpf: Filter out _GNU_SOURCE when compiling test_cpp") commit fdad456cbcca ("bpf: Fix updating attached freplace prog in prog_array map") No conflicts. Adjacent changes in: include/linux/bpf_verifier.h kernel/bpf/verifier.c tools/testing/selftests/bpf/Makefile Link: https://lore.kernel.org/bpf/20240813234307.82773-1-alexei.starovoitov@gmail.com/ Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Diffstat (limited to 'net')
-rw-r--r--net/bluetooth/hci_core.c7
-rw-r--r--net/bluetooth/hci_event.c5
-rw-r--r--net/bluetooth/hci_sync.c35
-rw-r--r--net/bluetooth/l2cap_core.c1
-rw-r--r--net/bridge/br_multicast.c4
-rw-r--r--net/bridge/br_netfilter_hooks.c6
-rw-r--r--net/core/dev.c27
-rw-r--r--net/core/link_watch.c4
-rw-r--r--net/core/rtnetlink.c2
-rw-r--r--net/ethtool/cmis_fw_update.c8
-rw-r--r--net/ethtool/ioctl.c61
-rw-r--r--net/ethtool/rss.c8
-rw-r--r--net/ipv4/netfilter/iptable_nat.c18
-rw-r--r--net/ipv4/proc.c2
-rw-r--r--net/ipv4/tcp_ao.c43
-rw-r--r--net/ipv4/tcp_input.c5
-rw-r--r--net/ipv4/tcp_offload.c3
-rw-r--r--net/ipv4/udp_offload.c10
-rw-r--r--net/ipv6/ndisc.c34
-rw-r--r--net/ipv6/netfilter/ip6table_nat.c14
-rw-r--r--net/ipv6/netfilter/nf_conntrack_reasm.c4
-rw-r--r--net/ipv6/proc.c2
-rw-r--r--net/iucv/af_iucv.c4
-rw-r--r--net/l2tp/l2tp_core.c15
-rw-r--r--net/mac80211/cfg.c7
-rw-r--r--net/mac80211/tx.c5
-rw-r--r--net/mac80211/util.c2
-rw-r--r--net/mptcp/diag.c2
-rw-r--r--net/mptcp/mib.c2
-rw-r--r--net/mptcp/mib.h2
-rw-r--r--net/mptcp/options.c5
-rw-r--r--net/mptcp/pm.c12
-rw-r--r--net/mptcp/pm_netlink.c93
-rw-r--r--net/mptcp/pm_userspace.c18
-rw-r--r--net/mptcp/protocol.c18
-rw-r--r--net/mptcp/protocol.h4
-rw-r--r--net/mptcp/subflow.c26
-rw-r--r--net/netfilter/nf_flow_table_offload.c2
-rw-r--r--net/netfilter/nf_tables_api.c147
-rw-r--r--net/netfilter/nfnetlink.c5
-rw-r--r--net/netfilter/nfnetlink_queue.c35
-rw-r--r--net/sched/act_ct.c4
-rw-r--r--net/sctp/input.c19
-rw-r--r--net/smc/af_smc.c7
-rw-r--r--net/smc/smc_stats.h2
-rw-r--r--net/sunrpc/svc.c2
-rw-r--r--net/vmw_vsock/af_vsock.c50
-rw-r--r--net/vmw_vsock/vsock_bpf.c4
-rw-r--r--net/wireless/scan.c11
-rw-r--r--net/wireless/sme.c1
50 files changed, 579 insertions, 228 deletions
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 8a4ebd93adfc..06da8ac13dca 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -119,13 +119,6 @@ void hci_discovery_set_state(struct hci_dev *hdev, int state)
case DISCOVERY_STARTING:
break;
case DISCOVERY_FINDING:
- /* If discovery was not started then it was initiated by the
- * MGMT interface so no MGMT event shall be generated either
- */
- if (old_state != DISCOVERY_STARTING) {
- hdev->discovery.state = old_state;
- return;
- }
mgmt_discovering(hdev, 1);
break;
case DISCOVERY_RESOLVING:
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index dce8035ca799..d0c118c47f6c 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -1721,9 +1721,10 @@ static void le_set_scan_enable_complete(struct hci_dev *hdev, u8 enable)
switch (enable) {
case LE_SCAN_ENABLE:
hci_dev_set_flag(hdev, HCI_LE_SCAN);
- if (hdev->le_scan_type == LE_SCAN_ACTIVE)
+ if (hdev->le_scan_type == LE_SCAN_ACTIVE) {
clear_pending_adv_report(hdev);
- hci_discovery_set_state(hdev, DISCOVERY_FINDING);
+ hci_discovery_set_state(hdev, DISCOVERY_FINDING);
+ }
break;
case LE_SCAN_DISABLE:
diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c
index cd2ed16da8a4..e79cd40bd079 100644
--- a/net/bluetooth/hci_sync.c
+++ b/net/bluetooth/hci_sync.c
@@ -2976,6 +2976,27 @@ static int hci_passive_scan_sync(struct hci_dev *hdev)
*/
filter_policy = hci_update_accept_list_sync(hdev);
+ /* If suspended and filter_policy set to 0x00 (no acceptlist) then
+ * passive scanning cannot be started since that would require the host
+ * to be woken up to process the reports.
+ */
+ if (hdev->suspended && !filter_policy) {
+ /* Check if accept list is empty then there is no need to scan
+ * while suspended.
+ */
+ if (list_empty(&hdev->le_accept_list))
+ return 0;
+
+ /* If there are devices is the accept_list that means some
+ * devices could not be programmed which in non-suspended case
+ * means filter_policy needs to be set to 0x00 so the host needs
+ * to filter, but since this is treating suspended case we
+ * can ignore device needing host to filter to allow devices in
+ * the acceptlist to be able to wakeup the system.
+ */
+ filter_policy = 0x01;
+ }
+
/* When the controller is using random resolvable addresses and
* with that having LE privacy enabled, then controllers with
* Extended Scanner Filter Policies support can now enable support
@@ -2998,6 +3019,20 @@ static int hci_passive_scan_sync(struct hci_dev *hdev)
} else if (hci_is_adv_monitoring(hdev)) {
window = hdev->le_scan_window_adv_monitor;
interval = hdev->le_scan_int_adv_monitor;
+
+ /* Disable duplicates filter when scanning for advertisement
+ * monitor for the following reasons.
+ *
+ * For HW pattern filtering (ex. MSFT), Realtek and Qualcomm
+ * controllers ignore RSSI_Sampling_Period when the duplicates
+ * filter is enabled.
+ *
+ * For SW pattern filtering, when we're not doing interleaved
+ * scanning, it is necessary to disable duplicates filter,
+ * otherwise hosts can only receive one advertisement and it's
+ * impossible to know if a peer is still in range.
+ */
+ filter_dups = LE_SCAN_FILTER_DUP_DISABLE;
} else {
window = hdev->le_scan_window;
interval = hdev->le_scan_interval;
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index c3c26bbb5dda..9988ba382b68 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -6774,6 +6774,7 @@ static void l2cap_conless_channel(struct l2cap_conn *conn, __le16 psm,
bt_cb(skb)->l2cap.psm = psm;
if (!chan->ops->recv(chan, skb)) {
+ l2cap_chan_unlock(chan);
l2cap_chan_put(chan);
return;
}
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index 9a1cb5079a7a..b2ae0d2434d2 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -2045,16 +2045,14 @@ void br_multicast_del_port(struct net_bridge_port *port)
{
struct net_bridge *br = port->br;
struct net_bridge_port_group *pg;
- HLIST_HEAD(deleted_head);
struct hlist_node *n;
/* Take care of the remaining groups, only perm ones should be left */
spin_lock_bh(&br->multicast_lock);
hlist_for_each_entry_safe(pg, n, &port->mglist, mglist)
br_multicast_find_del_pg(br, pg);
- hlist_move_list(&br->mcast_gc_list, &deleted_head);
spin_unlock_bh(&br->multicast_lock);
- br_multicast_gc(&deleted_head);
+ flush_work(&br->mcast_gc_work);
br_multicast_port_ctx_deinit(&port->multicast_ctx);
free_percpu(port->mcast_stats);
}
diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c
index 09f6a773a708..8f9c19d992ac 100644
--- a/net/bridge/br_netfilter_hooks.c
+++ b/net/bridge/br_netfilter_hooks.c
@@ -622,8 +622,12 @@ static unsigned int br_nf_local_in(void *priv,
if (likely(nf_ct_is_confirmed(ct)))
return NF_ACCEPT;
+ if (WARN_ON_ONCE(refcount_read(&nfct->use) != 1)) {
+ nf_reset_ct(skb);
+ return NF_ACCEPT;
+ }
+
WARN_ON_ONCE(skb_shared(skb));
- WARN_ON_ONCE(refcount_read(&nfct->use) != 1);
/* We can't call nf_confirm here, it would create a dependency
* on nf_conntrack module.
diff --git a/net/core/dev.c b/net/core/dev.c
index 6ea1d20676fb..f66e61407883 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5150,6 +5150,7 @@ int do_xdp_generic(struct bpf_prog *xdp_prog, struct sk_buff **pskb)
bpf_net_ctx_clear(bpf_net_ctx);
return XDP_DROP;
}
+ bpf_net_ctx_clear(bpf_net_ctx);
}
return XDP_PASS;
out_redir:
@@ -9911,6 +9912,15 @@ static void netdev_sync_lower_features(struct net_device *upper,
}
}
+static bool netdev_has_ip_or_hw_csum(netdev_features_t features)
+{
+ netdev_features_t ip_csum_mask = NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
+ bool ip_csum = (features & ip_csum_mask) == ip_csum_mask;
+ bool hw_csum = features & NETIF_F_HW_CSUM;
+
+ return ip_csum || hw_csum;
+}
+
static netdev_features_t netdev_fix_features(struct net_device *dev,
netdev_features_t features)
{
@@ -9992,15 +10002,9 @@ static netdev_features_t netdev_fix_features(struct net_device *dev,
features &= ~NETIF_F_LRO;
}
- if (features & NETIF_F_HW_TLS_TX) {
- bool ip_csum = (features & (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM)) ==
- (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM);
- bool hw_csum = features & NETIF_F_HW_CSUM;
-
- if (!ip_csum && !hw_csum) {
- netdev_dbg(dev, "Dropping TLS TX HW offload feature since no CSUM feature.\n");
- features &= ~NETIF_F_HW_TLS_TX;
- }
+ if ((features & NETIF_F_HW_TLS_TX) && !netdev_has_ip_or_hw_csum(features)) {
+ netdev_dbg(dev, "Dropping TLS TX HW offload feature since no CSUM feature.\n");
+ features &= ~NETIF_F_HW_TLS_TX;
}
if ((features & NETIF_F_HW_TLS_RX) && !(features & NETIF_F_RXCSUM)) {
@@ -10008,6 +10012,11 @@ static netdev_features_t netdev_fix_features(struct net_device *dev,
features &= ~NETIF_F_HW_TLS_RX;
}
+ if ((features & NETIF_F_GSO_UDP_L4) && !netdev_has_ip_or_hw_csum(features)) {
+ netdev_dbg(dev, "Dropping USO feature since no CSUM feature.\n");
+ features &= ~NETIF_F_GSO_UDP_L4;
+ }
+
return features;
}
diff --git a/net/core/link_watch.c b/net/core/link_watch.c
index 8ec35194bfcb..ab150641142a 100644
--- a/net/core/link_watch.c
+++ b/net/core/link_watch.c
@@ -148,9 +148,9 @@ static void linkwatch_schedule_work(int urgent)
* override the existing timer.
*/
if (test_bit(LW_URGENT, &linkwatch_flags))
- mod_delayed_work(system_wq, &linkwatch_work, 0);
+ mod_delayed_work(system_unbound_wq, &linkwatch_work, 0);
else
- schedule_delayed_work(&linkwatch_work, delay);
+ queue_delayed_work(system_unbound_wq, &linkwatch_work, delay);
}
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 87e67194f240..73fd7f543fd0 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -3288,7 +3288,7 @@ static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh,
if (ifm->ifi_index > 0)
dev = __dev_get_by_index(tgt_net, ifm->ifi_index);
else if (tb[IFLA_IFNAME] || tb[IFLA_ALT_IFNAME])
- dev = rtnl_dev_get(net, tb);
+ dev = rtnl_dev_get(tgt_net, tb);
else if (tb[IFLA_GROUP])
err = rtnl_group_dellink(tgt_net, nla_get_u32(tb[IFLA_GROUP]));
else
diff --git a/net/ethtool/cmis_fw_update.c b/net/ethtool/cmis_fw_update.c
index ae4b4b28a601..655ff5224ffa 100644
--- a/net/ethtool/cmis_fw_update.c
+++ b/net/ethtool/cmis_fw_update.c
@@ -35,7 +35,10 @@ struct cmis_cdb_fw_mng_features_rpl {
__be16 resv7;
};
-#define CMIS_CDB_FW_WRITE_MECHANISM_LPL 0x01
+enum cmis_cdb_fw_write_mechanism {
+ CMIS_CDB_FW_WRITE_MECHANISM_LPL = 0x01,
+ CMIS_CDB_FW_WRITE_MECHANISM_BOTH = 0x11,
+};
static int
cmis_fw_update_fw_mng_features_get(struct ethtool_cmis_cdb *cdb,
@@ -64,7 +67,8 @@ cmis_fw_update_fw_mng_features_get(struct ethtool_cmis_cdb *cdb,
}
rpl = (struct cmis_cdb_fw_mng_features_rpl *)args.req.payload;
- if (!(rpl->write_mechanism == CMIS_CDB_FW_WRITE_MECHANISM_LPL)) {
+ if (!(rpl->write_mechanism == CMIS_CDB_FW_WRITE_MECHANISM_LPL ||
+ rpl->write_mechanism == CMIS_CDB_FW_WRITE_MECHANISM_BOTH)) {
ethnl_module_fw_flash_ntf_err(dev, ntf_params,
"Write LPL is not supported",
NULL);
diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c
index 983fee76f5cf..e18823bf2330 100644
--- a/net/ethtool/ioctl.c
+++ b/net/ethtool/ioctl.c
@@ -1331,13 +1331,13 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev,
u32 rss_cfg_offset = offsetof(struct ethtool_rxfh, rss_config[0]);
const struct ethtool_ops *ops = dev->ethtool_ops;
u32 dev_indir_size = 0, dev_key_size = 0, i;
+ u32 user_indir_len = 0, indir_bytes = 0;
struct ethtool_rxfh_param rxfh_dev = {};
struct ethtool_rxfh_context *ctx = NULL;
struct netlink_ext_ack *extack = NULL;
struct ethtool_rxnfc rx_rings;
struct ethtool_rxfh rxfh;
bool locked = false; /* dev->ethtool->rss_lock taken */
- u32 indir_bytes = 0;
bool create = false;
u8 *rss_config;
int ret;
@@ -1369,23 +1369,25 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev,
return -EOPNOTSUPP;
create = rxfh.rss_context == ETH_RXFH_CONTEXT_ALLOC;
- /* If either indir, hash key or function is valid, proceed further.
- * Must request at least one change: indir size, hash key, function
- * or input transformation.
- */
if ((rxfh.indir_size &&
rxfh.indir_size != ETH_RXFH_INDIR_NO_CHANGE &&
rxfh.indir_size != dev_indir_size) ||
- (rxfh.key_size && (rxfh.key_size != dev_key_size)) ||
+ (rxfh.key_size && rxfh.key_size != dev_key_size))
+ return -EINVAL;
+
+ /* Must request at least one change: indir size, hash key, function
+ * or input transformation.
+ * There's no need for any of it in case of context creation.
+ */
+ if (!create &&
(rxfh.indir_size == ETH_RXFH_INDIR_NO_CHANGE &&
rxfh.key_size == 0 && rxfh.hfunc == ETH_RSS_HASH_NO_CHANGE &&
rxfh.input_xfrm == RXH_XFRM_NO_CHANGE))
return -EINVAL;
- if (rxfh.indir_size != ETH_RXFH_INDIR_NO_CHANGE)
- indir_bytes = dev_indir_size * sizeof(rxfh_dev.indir[0]);
+ indir_bytes = dev_indir_size * sizeof(rxfh_dev.indir[0]);
- rss_config = kzalloc(indir_bytes + rxfh.key_size, GFP_USER);
+ rss_config = kzalloc(indir_bytes + dev_key_size, GFP_USER);
if (!rss_config)
return -ENOMEM;
@@ -1400,6 +1402,7 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev,
*/
if (rxfh.indir_size &&
rxfh.indir_size != ETH_RXFH_INDIR_NO_CHANGE) {
+ user_indir_len = indir_bytes;
rxfh_dev.indir = (u32 *)rss_config;
rxfh_dev.indir_size = dev_indir_size;
ret = ethtool_copy_validate_indir(rxfh_dev.indir,
@@ -1426,7 +1429,7 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev,
rxfh_dev.key_size = dev_key_size;
rxfh_dev.key = rss_config + indir_bytes;
if (copy_from_user(rxfh_dev.key,
- useraddr + rss_cfg_offset + indir_bytes,
+ useraddr + rss_cfg_offset + user_indir_len,
rxfh.key_size)) {
ret = -EFAULT;
goto out;
@@ -1449,12 +1452,13 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev,
}
if (ops->create_rxfh_context) {
- u32 limit = ops->rxfh_max_context_id ?: U32_MAX;
+ u32 limit = ops->rxfh_max_num_contexts ?: U32_MAX;
u32 ctx_id;
/* driver uses new API, core allocates ID */
ret = xa_alloc(&dev->ethtool->rss_ctx, &ctx_id, ctx,
- XA_LIMIT(1, limit), GFP_KERNEL_ACCOUNT);
+ XA_LIMIT(1, limit - 1),
+ GFP_KERNEL_ACCOUNT);
if (ret < 0) {
kfree(ctx);
goto out;
@@ -1474,16 +1478,21 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev,
rxfh_dev.input_xfrm = rxfh.input_xfrm;
if (rxfh.rss_context && ops->create_rxfh_context) {
- if (create)
+ if (create) {
ret = ops->create_rxfh_context(dev, ctx, &rxfh_dev,
extack);
- else if (rxfh_dev.rss_delete)
+ /* Make sure driver populates defaults */
+ WARN_ON_ONCE(!ret && !rxfh_dev.key &&
+ !memchr_inv(ethtool_rxfh_context_key(ctx),
+ 0, ctx->key_size));
+ } else if (rxfh_dev.rss_delete) {
ret = ops->remove_rxfh_context(dev, ctx,
rxfh.rss_context,
extack);
- else
+ } else {
ret = ops->modify_rxfh_context(dev, ctx, &rxfh_dev,
extack);
+ }
} else {
ret = ops->set_rxfh(dev, &rxfh_dev, extack);
}
@@ -1522,6 +1531,22 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev,
kfree(ctx);
goto out;
}
+
+ /* Fetch the defaults for the old API, in the new API drivers
+ * should write defaults into ctx themselves.
+ */
+ rxfh_dev.indir = (u32 *)rss_config;
+ rxfh_dev.indir_size = dev_indir_size;
+
+ rxfh_dev.key = rss_config + indir_bytes;
+ rxfh_dev.key_size = dev_key_size;
+
+ ret = ops->get_rxfh(dev, &rxfh_dev);
+ if (WARN_ON(ret)) {
+ xa_erase(&dev->ethtool->rss_ctx, rxfh.rss_context);
+ kfree(ctx);
+ goto out;
+ }
}
if (rxfh_dev.rss_delete) {
WARN_ON(xa_erase(&dev->ethtool->rss_ctx, rxfh.rss_context) != ctx);
@@ -1530,12 +1555,14 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev,
if (rxfh_dev.indir) {
for (i = 0; i < dev_indir_size; i++)
ethtool_rxfh_context_indir(ctx)[i] = rxfh_dev.indir[i];
- ctx->indir_configured = 1;
+ ctx->indir_configured =
+ rxfh.indir_size &&
+ rxfh.indir_size != ETH_RXFH_INDIR_NO_CHANGE;
}
if (rxfh_dev.key) {
memcpy(ethtool_rxfh_context_key(ctx), rxfh_dev.key,
dev_key_size);
- ctx->key_configured = 1;
+ ctx->key_configured = !!rxfh.key_size;
}
if (rxfh_dev.hfunc != ETH_RSS_HASH_NO_CHANGE)
ctx->hfunc = rxfh_dev.hfunc;
diff --git a/net/ethtool/rss.c b/net/ethtool/rss.c
index 71679137eff2..5c4c4505ab9a 100644
--- a/net/ethtool/rss.c
+++ b/net/ethtool/rss.c
@@ -111,7 +111,8 @@ rss_reply_size(const struct ethnl_req_info *req_base,
const struct rss_reply_data *data = RSS_REPDATA(reply_base);
int len;
- len = nla_total_size(sizeof(u32)) + /* _RSS_HFUNC */
+ len = nla_total_size(sizeof(u32)) + /* _RSS_CONTEXT */
+ nla_total_size(sizeof(u32)) + /* _RSS_HFUNC */
nla_total_size(sizeof(u32)) + /* _RSS_INPUT_XFRM */
nla_total_size(sizeof(u32) * data->indir_size) + /* _RSS_INDIR */
nla_total_size(data->hkey_size); /* _RSS_HKEY */
@@ -124,6 +125,11 @@ rss_fill_reply(struct sk_buff *skb, const struct ethnl_req_info *req_base,
const struct ethnl_reply_data *reply_base)
{
const struct rss_reply_data *data = RSS_REPDATA(reply_base);
+ struct rss_req_info *request = RSS_REQINFO(req_base);
+
+ if (request->rss_context &&
+ nla_put_u32(skb, ETHTOOL_A_RSS_CONTEXT, request->rss_context))
+ return -EMSGSIZE;
if ((data->hfunc &&
nla_put_u32(skb, ETHTOOL_A_RSS_HFUNC, data->hfunc)) ||
diff --git a/net/ipv4/netfilter/iptable_nat.c b/net/ipv4/netfilter/iptable_nat.c
index 4d42d0756fd7..a5db7c67d61b 100644
--- a/net/ipv4/netfilter/iptable_nat.c
+++ b/net/ipv4/netfilter/iptable_nat.c
@@ -145,25 +145,27 @@ static struct pernet_operations iptable_nat_net_ops = {
static int __init iptable_nat_init(void)
{
- int ret = xt_register_template(&nf_nat_ipv4_table,
- iptable_nat_table_init);
+ int ret;
+ /* net->gen->ptr[iptable_nat_net_id] must be allocated
+ * before calling iptable_nat_table_init().
+ */
+ ret = register_pernet_subsys(&iptable_nat_net_ops);
if (ret < 0)
return ret;
- ret = register_pernet_subsys(&iptable_nat_net_ops);
- if (ret < 0) {
- xt_unregister_template(&nf_nat_ipv4_table);
- return ret;
- }
+ ret = xt_register_template(&nf_nat_ipv4_table,
+ iptable_nat_table_init);
+ if (ret < 0)
+ unregister_pernet_subsys(&iptable_nat_net_ops);
return ret;
}
static void __exit iptable_nat_exit(void)
{
- unregister_pernet_subsys(&iptable_nat_net_ops);
xt_unregister_template(&nf_nat_ipv4_table);
+ unregister_pernet_subsys(&iptable_nat_net_ops);
}
module_init(iptable_nat_init);
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index 6c4664c681ca..40053a02bae1 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -44,7 +44,7 @@
#include <net/sock.h>
#include <net/raw.h>
-#define TCPUDP_MIB_MAX max_t(u32, UDP_MIB_MAX, TCP_MIB_MAX)
+#define TCPUDP_MIB_MAX MAX_T(u32, UDP_MIB_MAX, TCP_MIB_MAX)
/*
* Report socket allocation statistics [mea@utu.fi]
diff --git a/net/ipv4/tcp_ao.c b/net/ipv4/tcp_ao.c
index 85531437890c..db6516092daf 100644
--- a/net/ipv4/tcp_ao.c
+++ b/net/ipv4/tcp_ao.c
@@ -267,32 +267,49 @@ static void tcp_ao_key_free_rcu(struct rcu_head *head)
kfree_sensitive(key);
}
-void tcp_ao_destroy_sock(struct sock *sk, bool twsk)
+static void tcp_ao_info_free_rcu(struct rcu_head *head)
{
- struct tcp_ao_info *ao;
+ struct tcp_ao_info *ao = container_of(head, struct tcp_ao_info, rcu);
struct tcp_ao_key *key;
struct hlist_node *n;
+ hlist_for_each_entry_safe(key, n, &ao->head, node) {
+ hlist_del(&key->node);
+ tcp_sigpool_release(key->tcp_sigpool_id);
+ kfree_sensitive(key);
+ }
+ kfree(ao);
+ static_branch_slow_dec_deferred(&tcp_ao_needed);
+}
+
+static void tcp_ao_sk_omem_free(struct sock *sk, struct tcp_ao_info *ao)
+{
+ size_t total_ao_sk_mem = 0;
+ struct tcp_ao_key *key;
+
+ hlist_for_each_entry(key, &ao->head, node)
+ total_ao_sk_mem += tcp_ao_sizeof_key(key);
+ atomic_sub(total_ao_sk_mem, &sk->sk_omem_alloc);
+}
+
+void tcp_ao_destroy_sock(struct sock *sk, bool twsk)
+{
+ struct tcp_ao_info *ao;
+
if (twsk) {
ao = rcu_dereference_protected(tcp_twsk(sk)->ao_info, 1);
- tcp_twsk(sk)->ao_info = NULL;
+ rcu_assign_pointer(tcp_twsk(sk)->ao_info, NULL);
} else {
ao = rcu_dereference_protected(tcp_sk(sk)->ao_info, 1);
- tcp_sk(sk)->ao_info = NULL;
+ rcu_assign_pointer(tcp_sk(sk)->ao_info, NULL);
}
if (!ao || !refcount_dec_and_test(&ao->refcnt))
return;
- hlist_for_each_entry_safe(key, n, &ao->head, node) {
- hlist_del_rcu(&key->node);
- if (!twsk)
- atomic_sub(tcp_ao_sizeof_key(key), &sk->sk_omem_alloc);
- call_rcu(&key->rcu, tcp_ao_key_free_rcu);
- }
-
- kfree_rcu(ao, rcu);
- static_branch_slow_dec_deferred(&tcp_ao_needed);
+ if (!twsk)
+ tcp_ao_sk_omem_free(sk, ao);
+ call_rcu(&ao->rcu, tcp_ao_info_free_rcu);
}
void tcp_ao_time_wait(struct tcp_timewait_sock *tcptw, struct tcp_sock *tp)
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 454362e359da..e37488d3453f 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -238,9 +238,14 @@ static void tcp_measure_rcv_mss(struct sock *sk, const struct sk_buff *skb)
*/
if (unlikely(len != icsk->icsk_ack.rcv_mss)) {
u64 val = (u64)skb->len << TCP_RMEM_TO_WIN_SCALE;
+ u8 old_ratio = tcp_sk(sk)->scaling_ratio;
do_div(val, skb->truesize);
tcp_sk(sk)->scaling_ratio = val ? val : 1;
+
+ if (old_ratio != tcp_sk(sk)->scaling_ratio)
+ WRITE_ONCE(tcp_sk(sk)->window_clamp,
+ tcp_win_from_space(sk, sk->sk_rcvbuf));
}
icsk->icsk_ack.rcv_mss = min_t(unsigned int, len,
tcp_sk(sk)->advmss);
diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
index 4b791e74529e..e4ad3311e148 100644
--- a/net/ipv4/tcp_offload.c
+++ b/net/ipv4/tcp_offload.c
@@ -140,6 +140,9 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb,
if (thlen < sizeof(*th))
goto out;
+ if (unlikely(skb_checksum_start(skb) != skb_transport_header(skb)))
+ goto out;
+
if (!pskb_may_pull(skb, thlen))
goto out;
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index aa2e0a28ca61..b254a5dadfcf 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -278,6 +278,16 @@ struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb,
if (gso_skb->len <= sizeof(*uh) + mss)
return ERR_PTR(-EINVAL);
+ if (unlikely(skb_checksum_start(gso_skb) !=
+ skb_transport_header(gso_skb)))
+ return ERR_PTR(-EINVAL);
+
+ /* We don't know if egress device can segment and checksum the packet
+ * when IPv6 extension headers are present. Fall back to software GSO.
+ */
+ if (gso_skb->ip_summed != CHECKSUM_PARTIAL)
+ features &= ~(NETIF_F_GSO_UDP_L4 | NETIF_F_CSUM_MASK);
+
if (skb_gso_ok(gso_skb, features | NETIF_F_GSO_ROBUST)) {
/* Packet is from an untrusted source, reset gso_segs. */
skb_shinfo(gso_skb)->gso_segs = DIV_ROUND_UP(gso_skb->len - sizeof(*uh),
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 70a0b2ad6bd7..b8eec1b6cc2c 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -227,6 +227,7 @@ struct ndisc_options *ndisc_parse_options(const struct net_device *dev,
return NULL;
memset(ndopts, 0, sizeof(*ndopts));
while (opt_len) {
+ bool unknown = false;
int l;
if (opt_len < sizeof(struct nd_opt_hdr))
return NULL;
@@ -262,22 +263,23 @@ struct ndisc_options *ndisc_parse_options(const struct net_device *dev,
break;
#endif
default:
- if (ndisc_is_useropt(dev, nd_opt)) {
- ndopts->nd_useropts_end = nd_opt;
- if (!ndopts->nd_useropts)
- ndopts->nd_useropts = nd_opt;
- } else {
- /*
- * Unknown options must be silently ignored,
- * to accommodate future extension to the
- * protocol.
- */
- ND_PRINTK(2, notice,
- "%s: ignored unsupported option; type=%d, len=%d\n",
- __func__,
- nd_opt->nd_opt_type,
- nd_opt->nd_opt_len);
- }
+ unknown = true;
+ }
+ if (ndisc_is_useropt(dev, nd_opt)) {
+ ndopts->nd_useropts_end = nd_opt;
+ if (!ndopts->nd_useropts)
+ ndopts->nd_useropts = nd_opt;
+ } else if (unknown) {
+ /*
+ * Unknown options must be silently ignored,
+ * to accommodate future extension to the
+ * protocol.
+ */
+ ND_PRINTK(2, notice,
+ "%s: ignored unsupported option; type=%d, len=%d\n",
+ __func__,
+ nd_opt->nd_opt_type,
+ nd_opt->nd_opt_len);
}
next_opt:
opt_len -= l;
diff --git a/net/ipv6/netfilter/ip6table_nat.c b/net/ipv6/netfilter/ip6table_nat.c
index 52cf104e3478..e119d4f090cc 100644
--- a/net/ipv6/netfilter/ip6table_nat.c
+++ b/net/ipv6/netfilter/ip6table_nat.c
@@ -147,23 +147,27 @@ static struct pernet_operations ip6table_nat_net_ops = {
static int __init ip6table_nat_init(void)
{
- int ret = xt_register_template(&nf_nat_ipv6_table,
- ip6table_nat_table_init);
+ int ret;
+ /* net->gen->ptr[ip6table_nat_net_id] must be allocated
+ * before calling ip6t_nat_register_lookups().
+ */
+ ret = register_pernet_subsys(&ip6table_nat_net_ops);
if (ret < 0)
return ret;
- ret = register_pernet_subsys(&ip6table_nat_net_ops);
+ ret = xt_register_template(&nf_nat_ipv6_table,
+ ip6table_nat_table_init);
if (ret)
- xt_unregister_template(&nf_nat_ipv6_table);
+ unregister_pernet_subsys(&ip6table_nat_net_ops);
return ret;
}
static void __exit ip6table_nat_exit(void)
{
- unregister_pernet_subsys(&ip6table_nat_net_ops);
xt_unregister_template(&nf_nat_ipv6_table);
+ unregister_pernet_subsys(&ip6table_nat_net_ops);
}
module_init(ip6table_nat_init);
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index 6f0844c9315d..4120e67a8ce6 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -154,6 +154,10 @@ static struct frag_queue *fq_find(struct net *net, __be32 id, u32 user,
};
struct inet_frag_queue *q;
+ if (!(ipv6_addr_type(&hdr->daddr) & (IPV6_ADDR_MULTICAST |
+ IPV6_ADDR_LINKLOCAL)))
+ key.iif = 0;
+
q = inet_frag_find(nf_frag->fqdir, &key);
if (!q)
return NULL;
diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c
index 6d1d9221649d..752327b10dde 100644
--- a/net/ipv6/proc.c
+++ b/net/ipv6/proc.c
@@ -27,7 +27,7 @@
#include <net/ipv6.h>
#define MAX4(a, b, c, d) \
- max_t(u32, max_t(u32, a, b), max_t(u32, c, d))
+ MAX_T(u32, MAX_T(u32, a, b), MAX_T(u32, c, d))
#define SNMP_MIB_MAX MAX4(UDP_MIB_MAX, TCP_MIB_MAX, \
IPSTATS_MIB_MAX, ICMP_MIB_MAX)
diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c
index c3b0b610b0aa..c00323fa9eb6 100644
--- a/net/iucv/af_iucv.c
+++ b/net/iucv/af_iucv.c
@@ -335,8 +335,8 @@ static void iucv_sever_path(struct sock *sk, int with_user_data)
struct iucv_sock *iucv = iucv_sk(sk);
struct iucv_path *path = iucv->path;
- if (iucv->path) {
- iucv->path = NULL;
+ /* Whoever resets the path pointer, must sever and free it. */
+ if (xchg(&iucv->path, NULL)) {
if (with_user_data) {
low_nmcpy(user_data, iucv->src_name);
high_nmcpy(user_data, iucv->dst_name);
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index c80ab3f26084..2e86f520f799 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -86,6 +86,11 @@
/* Default trace flags */
#define L2TP_DEFAULT_DEBUG_FLAGS 0
+#define L2TP_DEPTH_NESTING 2
+#if L2TP_DEPTH_NESTING == SINGLE_DEPTH_NESTING
+#error "L2TP requires its own lockdep subclass"
+#endif
+
/* Private data stored for received packets in the skb.
*/
struct l2tp_skb_cb {
@@ -1124,7 +1129,13 @@ static int l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb, uns
IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED | IPSKB_REROUTED);
nf_reset_ct(skb);
- bh_lock_sock_nested(sk);
+ /* L2TP uses its own lockdep subclass to avoid lockdep splats caused by
+ * nested socket calls on the same lockdep socket class. This can
+ * happen when data from a user socket is routed over l2tp, which uses
+ * another userspace socket.
+ */
+ spin_lock_nested(&sk->sk_lock.slock, L2TP_DEPTH_NESTING);
+
if (sock_owned_by_user(sk)) {
kfree_skb(skb);
ret = NET_XMIT_DROP;
@@ -1176,7 +1187,7 @@ static int l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb, uns
ret = l2tp_xmit_queue(tunnel, skb, &inet->cork.fl);
out_unlock:
- bh_unlock_sock(sk);
+ spin_unlock(&sk->sk_lock.slock);
return ret;
}
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 85cb71de370f..b02b84ce2130 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -114,7 +114,7 @@ static int ieee80211_set_mon_options(struct ieee80211_sub_if_data *sdata,
/* apply all changes now - no failures allowed */
- if (monitor_sdata)
+ if (monitor_sdata && ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF))
ieee80211_set_mu_mimo_follow(monitor_sdata, params);
if (params->flags) {
@@ -3053,6 +3053,9 @@ static int ieee80211_set_tx_power(struct wiphy *wiphy,
sdata = IEEE80211_WDEV_TO_SUB_IF(wdev);
if (sdata->vif.type == NL80211_IFTYPE_MONITOR) {
+ if (!ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF))
+ return -EOPNOTSUPP;
+
sdata = wiphy_dereference(local->hw.wiphy,
local->monitor_sdata);
if (!sdata)
@@ -3115,7 +3118,7 @@ static int ieee80211_set_tx_power(struct wiphy *wiphy,
if (has_monitor) {
sdata = wiphy_dereference(local->hw.wiphy,
local->monitor_sdata);
- if (sdata) {
+ if (sdata && ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF)) {
sdata->deflink.user_power_level = local->user_power_level;
if (txp_type != sdata->vif.bss_conf.txpower_type)
update_txp_type = true;
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 72a9ba8bc5fd..edba4a31844f 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -1768,7 +1768,7 @@ static bool __ieee80211_tx(struct ieee80211_local *local,
break;
}
sdata = rcu_dereference(local->monitor_sdata);
- if (sdata) {
+ if (sdata && ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF)) {
vif = &sdata->vif;
info->hw_queue =
vif->hw_queue[skb_get_queue_mapping(skb)];
@@ -3957,7 +3957,8 @@ begin:
break;
}
tx.sdata = rcu_dereference(local->monitor_sdata);
- if (tx.sdata) {
+ if (tx.sdata &&
+ ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF)) {
vif = &tx.sdata->vif;
info->hw_queue =
vif->hw_queue[skb_get_queue_mapping(skb)];
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index ced19ce7c51a..c7ad9bc5973a 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -776,7 +776,7 @@ static void __iterate_interfaces(struct ieee80211_local *local,
sdata = rcu_dereference_check(local->monitor_sdata,
lockdep_is_held(&local->iflist_mtx) ||
lockdep_is_held(&local->hw.wiphy->mtx));
- if (sdata &&
+ if (sdata && ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF) &&
(iter_flags & IEEE80211_IFACE_ITER_RESUME_ALL || !active_only ||
sdata->flags & IEEE80211_SDATA_IN_DRIVER))
iterator(data, sdata->vif.addr, &sdata->vif);
diff --git a/net/mptcp/diag.c b/net/mptcp/diag.c
index 3ae46b545d2c..2d3efb405437 100644
--- a/net/mptcp/diag.c
+++ b/net/mptcp/diag.c
@@ -94,7 +94,7 @@ static size_t subflow_get_info_size(const struct sock *sk)
nla_total_size(4) + /* MPTCP_SUBFLOW_ATTR_RELWRITE_SEQ */
nla_total_size_64bit(8) + /* MPTCP_SUBFLOW_ATTR_MAP_SEQ */
nla_total_size(4) + /* MPTCP_SUBFLOW_ATTR_MAP_SFSEQ */
- nla_total_size(2) + /* MPTCP_SUBFLOW_ATTR_SSN_OFFSET */
+ nla_total_size(4) + /* MPTCP_SUBFLOW_ATTR_SSN_OFFSET */
nla_total_size(2) + /* MPTCP_SUBFLOW_ATTR_MAP_DATALEN */
nla_total_size(4) + /* MPTCP_SUBFLOW_ATTR_FLAGS */
nla_total_size(1) + /* MPTCP_SUBFLOW_ATTR_ID_REM */
diff --git a/net/mptcp/mib.c b/net/mptcp/mib.c
index c30405e76833..7884217f33eb 100644
--- a/net/mptcp/mib.c
+++ b/net/mptcp/mib.c
@@ -19,7 +19,9 @@ static const struct snmp_mib mptcp_snmp_list[] = {
SNMP_MIB_ITEM("MPTCPRetrans", MPTCP_MIB_RETRANSSEGS),
SNMP_MIB_ITEM("MPJoinNoTokenFound", MPTCP_MIB_JOINNOTOKEN),
SNMP_MIB_ITEM("MPJoinSynRx", MPTCP_MIB_JOINSYNRX),
+ SNMP_MIB_ITEM("MPJoinSynBackupRx", MPTCP_MIB_JOINSYNBACKUPRX),
SNMP_MIB_ITEM("MPJoinSynAckRx", MPTCP_MIB_JOINSYNACKRX),
+ SNMP_MIB_ITEM("MPJoinSynAckBackupRx", MPTCP_MIB_JOINSYNACKBACKUPRX),
SNMP_MIB_ITEM("MPJoinSynAckHMacFailure", MPTCP_MIB_JOINSYNACKMAC),
SNMP_MIB_ITEM("MPJoinAckRx", MPTCP_MIB_JOINACKRX),
SNMP_MIB_ITEM("MPJoinAckHMacFailure", MPTCP_MIB_JOINACKMAC),
diff --git a/net/mptcp/mib.h b/net/mptcp/mib.h
index 2704afd0dfe4..66aa67f49d03 100644
--- a/net/mptcp/mib.h
+++ b/net/mptcp/mib.h
@@ -14,7 +14,9 @@ enum linux_mptcp_mib_field {
MPTCP_MIB_RETRANSSEGS, /* Segments retransmitted at the MPTCP-level */
MPTCP_MIB_JOINNOTOKEN, /* Received MP_JOIN but the token was not found */
MPTCP_MIB_JOINSYNRX, /* Received a SYN + MP_JOIN */
+ MPTCP_MIB_JOINSYNBACKUPRX, /* Received a SYN + MP_JOIN + backup flag */
MPTCP_MIB_JOINSYNACKRX, /* Received a SYN/ACK + MP_JOIN */
+ MPTCP_MIB_JOINSYNACKBACKUPRX, /* Received a SYN/ACK + MP_JOIN + backup flag */
MPTCP_MIB_JOINSYNACKMAC, /* HMAC was wrong on SYN/ACK + MP_JOIN */
MPTCP_MIB_JOINACKRX, /* Received an ACK + MP_JOIN */
MPTCP_MIB_JOINACKMAC, /* HMAC was wrong on ACK + MP_JOIN */
diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index 8e8dcfbc2993..ac2f1a54cc43 100644
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -909,7 +909,7 @@ bool mptcp_synack_options(const struct request_sock *req, unsigned int *size,
return true;
} else if (subflow_req->mp_join) {
opts->suboptions = OPTION_MPTCP_MPJ_SYNACK;
- opts->backup = subflow_req->backup;
+ opts->backup = subflow_req->request_bkup;
opts->join_id = subflow_req->local_id;
opts->thmac = subflow_req->thmac;
opts->nonce = subflow_req->local_nonce;
@@ -958,7 +958,8 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *ssk,
if (subflow->remote_key_valid &&
(((mp_opt->suboptions & OPTION_MPTCP_DSS) && mp_opt->use_ack) ||
- ((mp_opt->suboptions & OPTION_MPTCP_ADD_ADDR) && !mp_opt->echo))) {
+ ((mp_opt->suboptions & OPTION_MPTCP_ADD_ADDR) &&
+ (!mp_opt->echo || subflow->mp_join)))) {
/* subflows are fully established as soon as we get any
* additional ack, including ADD_ADDR.
*/
diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index 55406720c607..23bb89c94e90 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -426,6 +426,18 @@ int mptcp_pm_get_local_id(struct mptcp_sock *msk, struct sock_common *skc)
return mptcp_pm_nl_get_local_id(msk, &skc_local);
}
+bool mptcp_pm_is_backup(struct mptcp_sock *msk, struct sock_common *skc)
+{
+ struct mptcp_addr_info skc_local;
+
+ mptcp_local_address((struct sock_common *)skc, &skc_local);
+
+ if (mptcp_pm_is_userspace(msk))
+ return mptcp_userspace_pm_is_backup(msk, &skc_local);
+
+ return mptcp_pm_nl_is_backup(msk, &skc_local);
+}
+
int mptcp_pm_get_flags_and_ifindex_by_id(struct mptcp_sock *msk, unsigned int id,
u8 *flags, int *ifindex)
{
diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index ea9e5817b9e9..4cae2aa7be5c 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -348,7 +348,7 @@ bool mptcp_pm_alloc_anno_list(struct mptcp_sock *msk,
add_entry = mptcp_lookup_anno_list_by_saddr(msk, addr);
if (add_entry) {
- if (mptcp_pm_is_kernel(msk))
+ if (WARN_ON_ONCE(mptcp_pm_is_kernel(msk)))
return false;
sk_reset_timer(sk, &add_entry->add_timer,
@@ -471,7 +471,6 @@ static void __mptcp_pm_send_ack(struct mptcp_sock *msk, struct mptcp_subflow_con
slow = lock_sock_fast(ssk);
if (prio) {
subflow->send_mp_prio = 1;
- subflow->backup = backup;
subflow->request_bkup = backup;
}
@@ -513,8 +512,8 @@ __lookup_addr(struct pm_nl_pernet *pernet, const struct mptcp_addr_info *info)
static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk)
{
+ struct mptcp_pm_addr_entry *local, *signal_and_subflow = NULL;
struct sock *sk = (struct sock *)msk;
- struct mptcp_pm_addr_entry *local;
unsigned int add_addr_signal_max;
unsigned int local_addr_max;
struct pm_nl_pernet *pernet;
@@ -556,8 +555,6 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk)
/* check first for announce */
if (msk->pm.add_addr_signaled < add_addr_signal_max) {
- local = select_signal_address(pernet, msk);
-
/* due to racing events on both ends we can reach here while
* previous add address is still running: if we invoke now
* mptcp_pm_announce_addr(), that will fail and the
@@ -568,16 +565,26 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk)
if (msk->pm.addr_signal & BIT(MPTCP_ADD_ADDR_SIGNAL))
return;
- if (local) {
- if (mptcp_pm_alloc_anno_list(msk, &local->addr)) {
- __clear_bit(local->addr.id, msk->pm.id_avail_bitmap);
- msk->pm.add_addr_signaled++;
- mptcp_pm_announce_addr(msk, &local->addr, false);
- mptcp_pm_nl_addr_send_ack(msk);
- }
- }
+ local = select_signal_address(pernet, msk);
+ if (!local)
+ goto subflow;
+
+ /* If the alloc fails, we are on memory pressure, not worth
+ * continuing, and trying to create subflows.
+ */
+ if (!mptcp_pm_alloc_anno_list(msk, &local->addr))
+ return;
+
+ __clear_bit(local->addr.id, msk->pm.id_avail_bitmap);
+ msk->pm.add_addr_signaled++;
+ mptcp_pm_announce_addr(msk, &local->addr, false);
+ mptcp_pm_nl_addr_send_ack(msk);
+
+ if (local->flags & MPTCP_PM_ADDR_FLAG_SUBFLOW)
+ signal_and_subflow = local;
}
+subflow:
/* check if should create a new subflow */
while (msk->pm.local_addr_used < local_addr_max &&
msk->pm.subflows < subflows_max) {
@@ -585,9 +592,14 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk)
bool fullmesh;
int i, nr;
- local = select_local_address(pernet, msk);
- if (!local)
- break;
+ if (signal_and_subflow) {
+ local = signal_and_subflow;
+ signal_and_subflow = NULL;
+ } else {
+ local = select_local_address(pernet, msk);
+ if (!local)
+ break;
+ }
fullmesh = !!(local->flags & MPTCP_PM_ADDR_FLAG_FULLMESH);
@@ -1102,6 +1114,24 @@ int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc
return ret;
}
+bool mptcp_pm_nl_is_backup(struct mptcp_sock *msk, struct mptcp_addr_info *skc)
+{
+ struct pm_nl_pernet *pernet = pm_nl_get_pernet_from_msk(msk);
+ struct mptcp_pm_addr_entry *entry;
+ bool backup = false;
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(entry, &pernet->local_addr_list, list) {
+ if (mptcp_addresses_equal(&entry->addr, skc, entry->addr.port)) {
+ backup = !!(entry->flags & MPTCP_PM_ADDR_FLAG_BACKUP);
+ break;
+ }
+ }
+ rcu_read_unlock();
+
+ return backup;
+}
+
#define MPTCP_PM_CMD_GRP_OFFSET 0
#define MPTCP_PM_EV_GRP_OFFSET 1
@@ -1311,8 +1341,8 @@ int mptcp_pm_nl_add_addr_doit(struct sk_buff *skb, struct genl_info *info)
if (ret < 0)
return ret;
- if (addr.addr.port && !(addr.flags & MPTCP_PM_ADDR_FLAG_SIGNAL)) {
- GENL_SET_ERR_MSG(info, "flags must have signal when using port");
+ if (addr.addr.port && !address_use_port(&addr)) {
+ GENL_SET_ERR_MSG(info, "flags must have signal and not subflow when using port");
return -EINVAL;
}
@@ -1401,6 +1431,7 @@ static bool mptcp_pm_remove_anno_addr(struct mptcp_sock *msk,
ret = remove_anno_list_by_saddr(msk, addr);
if (ret || force) {
spin_lock_bh(&msk->pm.lock);
+ msk->pm.add_addr_signaled -= ret;
mptcp_pm_remove_addr(msk, &list);
spin_unlock_bh(&msk->pm.lock);
}
@@ -1534,16 +1565,25 @@ void mptcp_pm_remove_addrs(struct mptcp_sock *msk, struct list_head *rm_list)
{
struct mptcp_rm_list alist = { .nr = 0 };
struct mptcp_pm_addr_entry *entry;
+ int anno_nr = 0;
list_for_each_entry(entry, rm_list, list) {
- if ((remove_anno_list_by_saddr(msk, &entry->addr) ||
- lookup_subflow_by_saddr(&msk->conn_list, &entry->addr)) &&
- alist.nr < MPTCP_RM_IDS_MAX)
- alist.ids[alist.nr++] = entry->addr.id;
+ if (alist.nr >= MPTCP_RM_IDS_MAX)
+ break;
+
+ /* only delete if either announced or matching a subflow */
+ if (remove_anno_list_by_saddr(msk, &entry->addr))
+ anno_nr++;
+ else if (!lookup_subflow_by_saddr(&msk->conn_list,
+ &entry->addr))
+ continue;
+
+ alist.ids[alist.nr++] = entry->addr.id;
}
if (alist.nr) {
spin_lock_bh(&msk->pm.lock);
+ msk->pm.add_addr_signaled -= anno_nr;
mptcp_pm_remove_addr(msk, &alist);
spin_unlock_bh(&msk->pm.lock);
}
@@ -1556,17 +1596,18 @@ static void mptcp_pm_remove_addrs_and_subflows(struct mptcp_sock *msk,
struct mptcp_pm_addr_entry *entry;
list_for_each_entry(entry, rm_list, list) {
- if (lookup_subflow_by_saddr(&msk->conn_list, &entry->addr) &&
- slist.nr < MPTCP_RM_IDS_MAX)
+ if (slist.nr < MPTCP_RM_IDS_MAX &&
+ lookup_subflow_by_saddr(&msk->conn_list, &entry->addr))
slist.ids[slist.nr++] = entry->addr.id;
- if (remove_anno_list_by_saddr(msk, &entry->addr) &&
- alist.nr < MPTCP_RM_IDS_MAX)
+ if (alist.nr < MPTCP_RM_IDS_MAX &&
+ remove_anno_list_by_saddr(msk, &entry->addr))
alist.ids[alist.nr++] = entry->addr.id;
}
if (alist.nr) {
spin_lock_bh(&msk->pm.lock);
+ msk->pm.add_addr_signaled -= alist.nr;
mptcp_pm_remove_addr(msk, &alist);
spin_unlock_bh(&msk->pm.lock);
}
diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c
index f0a4590506c6..8eaa9fbe3e34 100644
--- a/net/mptcp/pm_userspace.c
+++ b/net/mptcp/pm_userspace.c
@@ -165,6 +165,24 @@ int mptcp_userspace_pm_get_local_id(struct mptcp_sock *msk,
return mptcp_userspace_pm_append_new_local_addr(msk, &new_entry, true);
}
+bool mptcp_userspace_pm_is_backup(struct mptcp_sock *msk,
+ struct mptcp_addr_info *skc)
+{
+ struct mptcp_pm_addr_entry *entry;
+ bool backup = false;
+
+ spin_lock_bh(&msk->pm.lock);
+ list_for_each_entry(entry, &msk->pm.userspace_pm_local_addr_list, list) {
+ if (mptcp_addresses_equal(&entry->addr, skc, false)) {
+ backup = !!(entry->flags & MPTCP_PM_ADDR_FLAG_BACKUP);
+ break;
+ }
+ }
+ spin_unlock_bh(&msk->pm.lock);
+
+ return backup;
+}
+
int mptcp_pm_nl_announce_doit(struct sk_buff *skb, struct genl_info *info)
{
struct nlattr *token = info->attrs[MPTCP_PM_ATTR_TOKEN];
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index a26c2c840fd9..0d536b183a6c 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -350,8 +350,10 @@ static bool __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk,
skb_orphan(skb);
/* try to fetch required memory from subflow */
- if (!mptcp_rmem_schedule(sk, ssk, skb->truesize))
+ if (!mptcp_rmem_schedule(sk, ssk, skb->truesize)) {
+ MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RCVPRUNED);
goto drop;
+ }
has_rxtstamp = TCP_SKB_CB(skb)->has_rxtstamp;
@@ -844,10 +846,8 @@ void mptcp_data_ready(struct sock *sk, struct sock *ssk)
sk_rbuf = ssk_rbuf;
/* over limit? can't append more skbs to msk, Also, no need to wake-up*/
- if (__mptcp_rmem(sk) > sk_rbuf) {
- MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RCVPRUNED);
+ if (__mptcp_rmem(sk) > sk_rbuf)
return;
- }
/* Wake-up the reader only for in-sequence data */
mptcp_data_lock(sk);
@@ -1422,13 +1422,15 @@ struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk)
}
mptcp_for_each_subflow(msk, subflow) {
+ bool backup = subflow->backup || subflow->request_bkup;
+
trace_mptcp_subflow_get_send(subflow);
ssk = mptcp_subflow_tcp_sock(subflow);
if (!mptcp_subflow_active(subflow))
continue;
tout = max(tout, mptcp_timeout_from_subflow(subflow));
- nr_active += !subflow->backup;
+ nr_active += !backup;
pace = subflow->avg_pacing_rate;
if (unlikely(!pace)) {
/* init pacing rate from socket */
@@ -1439,9 +1441,9 @@ struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk)
}
linger_time = div_u64((u64)READ_ONCE(ssk->sk_wmem_queued) << 32, pace);
- if (linger_time < send_info[subflow->backup].linger_time) {
- send_info[subflow->backup].ssk = ssk;
- send_info[subflow->backup].linger_time = linger_time;
+ if (linger_time < send_info[backup].linger_time) {
+ send_info[backup].ssk = ssk;
+ send_info[backup].linger_time = linger_time;
}
}
__mptcp_set_timeout(sk, tout);
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index b11a4e50d52b..60c6b073d65f 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -448,6 +448,7 @@ struct mptcp_subflow_request_sock {
u16 mp_capable : 1,
mp_join : 1,
backup : 1,
+ request_bkup : 1,
csum_reqd : 1,
allow_join_id0 : 1;
u8 local_id;
@@ -1108,6 +1109,9 @@ bool mptcp_pm_rm_addr_signal(struct mptcp_sock *msk, unsigned int remaining,
int mptcp_pm_get_local_id(struct mptcp_sock *msk, struct sock_common *skc);
int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc);
int mptcp_userspace_pm_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc);
+bool mptcp_pm_is_backup(struct mptcp_sock *msk, struct sock_common *skc);
+bool mptcp_pm_nl_is_backup(struct mptcp_sock *msk, struct mptcp_addr_info *skc);
+bool mptcp_userspace_pm_is_backup(struct mptcp_sock *msk, struct mptcp_addr_info *skc);
int mptcp_pm_dump_addr(struct sk_buff *msg, struct netlink_callback *cb);
int mptcp_pm_nl_dump_addr(struct sk_buff *msg,
struct netlink_callback *cb);
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 39e2cbdf3801..a21c712350c3 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -100,6 +100,7 @@ static struct mptcp_sock *subflow_token_join_request(struct request_sock *req)
return NULL;
}
subflow_req->local_id = local_id;
+ subflow_req->request_bkup = mptcp_pm_is_backup(msk, (struct sock_common *)req);
return msk;
}
@@ -168,6 +169,9 @@ static int subflow_check_req(struct request_sock *req,
return 0;
} else if (opt_mp_join) {
SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINSYNRX);
+
+ if (mp_opt.backup)
+ SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINSYNBACKUPRX);
}
if (opt_mp_capable && listener->request_mptcp) {
@@ -577,6 +581,9 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
subflow->mp_join = 1;
MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINSYNACKRX);
+ if (subflow->backup)
+ MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINSYNACKBACKUPRX);
+
if (subflow_use_different_dport(msk, sk)) {
pr_debug("synack inet_dport=%d %d",
ntohs(inet_sk(sk)->inet_dport),
@@ -614,6 +621,8 @@ static int subflow_chk_local_id(struct sock *sk)
return err;
subflow_set_local_id(subflow, err);
+ subflow->request_bkup = mptcp_pm_is_backup(msk, (struct sock_common *)sk);
+
return 0;
}
@@ -1221,14 +1230,22 @@ static void mptcp_subflow_discard_data(struct sock *ssk, struct sk_buff *skb,
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
bool fin = TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN;
- u32 incr;
+ struct tcp_sock *tp = tcp_sk(ssk);
+ u32 offset, incr, avail_len;
- incr = limit >= skb->len ? skb->len + fin : limit;
+ offset = tp->copied_seq - TCP_SKB_CB(skb)->seq;
+ if (WARN_ON_ONCE(offset > skb->len))
+ goto out;
- pr_debug("discarding=%d len=%d seq=%d", incr, skb->len,
- subflow->map_subflow_seq);
+ avail_len = skb->len - offset;
+ incr = limit >= avail_len ? avail_len + fin : limit;
+
+ pr_debug("discarding=%d len=%d offset=%d seq=%d", incr, skb->len,
+ offset, subflow->map_subflow_seq);
MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_DUPDATA);
tcp_sk(ssk)->copied_seq += incr;
+
+out:
if (!before(tcp_sk(ssk)->copied_seq, TCP_SKB_CB(skb)->end_seq))
sk_eat_skb(ssk, skb);
if (mptcp_subflow_get_map_offset(subflow) >= subflow->map_data_len)
@@ -2005,6 +2022,7 @@ static void subflow_ulp_clone(const struct request_sock *req,
new_ctx->fully_established = 1;
new_ctx->remote_key_valid = 1;
new_ctx->backup = subflow_req->backup;
+ new_ctx->request_bkup = subflow_req->request_bkup;
WRITE_ONCE(new_ctx->remote_id, subflow_req->remote_id);
new_ctx->token = subflow_req->token;
new_ctx->thmac = subflow_req->thmac;
diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c
index ff1a4e36c2b5..e06bc36f49fe 100644
--- a/net/netfilter/nf_flow_table_offload.c
+++ b/net/netfilter/nf_flow_table_offload.c
@@ -841,8 +841,8 @@ static int nf_flow_offload_tuple(struct nf_flowtable *flowtable,
struct list_head *block_cb_list)
{
struct flow_cls_offload cls_flow = {};
+ struct netlink_ext_ack extack = {};
struct flow_block_cb *block_cb;
- struct netlink_ext_ack extack;
__be16 proto = ETH_P_ALL;
int err, i = 0;
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 481ee78e77bc..0a2f79346958 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -8020,6 +8020,19 @@ cont:
return skb->len;
}
+static int nf_tables_dumpreset_obj(struct sk_buff *skb,
+ struct netlink_callback *cb)
+{
+ struct nftables_pernet *nft_net = nft_pernet(sock_net(skb->sk));
+ int ret;
+
+ mutex_lock(&nft_net->commit_mutex);
+ ret = nf_tables_dump_obj(skb, cb);
+ mutex_unlock(&nft_net->commit_mutex);
+
+ return ret;
+}
+
static int nf_tables_dump_obj_start(struct netlink_callback *cb)
{
struct nft_obj_dump_ctx *ctx = (void *)cb->ctx;
@@ -8036,12 +8049,18 @@ static int nf_tables_dump_obj_start(struct netlink_callback *cb)
if (nla[NFTA_OBJ_TYPE])
ctx->type = ntohl(nla_get_be32(nla[NFTA_OBJ_TYPE]));
- if (NFNL_MSG_TYPE(cb->nlh->nlmsg_type) == NFT_MSG_GETOBJ_RESET)
- ctx->reset = true;
-
return 0;
}
+static int nf_tables_dumpreset_obj_start(struct netlink_callback *cb)
+{
+ struct nft_obj_dump_ctx *ctx = (void *)cb->ctx;
+
+ ctx->reset = true;
+
+ return nf_tables_dump_obj_start(cb);
+}
+
static int nf_tables_dump_obj_done(struct netlink_callback *cb)
{
struct nft_obj_dump_ctx *ctx = (void *)cb->ctx;
@@ -8052,8 +8071,9 @@ static int nf_tables_dump_obj_done(struct netlink_callback *cb)
}
/* called with rcu_read_lock held */
-static int nf_tables_getobj(struct sk_buff *skb, const struct nfnl_info *info,
- const struct nlattr * const nla[])
+static struct sk_buff *
+nf_tables_getobj_single(u32 portid, const struct nfnl_info *info,
+ const struct nlattr * const nla[], bool reset)
{
struct netlink_ext_ack *extack = info->extack;
u8 genmask = nft_genmask_cur(info->net);
@@ -8062,72 +8082,109 @@ static int nf_tables_getobj(struct sk_buff *skb, const struct nfnl_info *info,
struct net *net = info->net;
struct nft_object *obj;
struct sk_buff *skb2;
- bool reset = false;
u32 objtype;
int err;
- if (info->nlh->nlmsg_flags & NLM_F_DUMP) {
- struct netlink_dump_control c = {
- .start = nf_tables_dump_obj_start,
- .dump = nf_tables_dump_obj,
- .done = nf_tables_dump_obj_done,
- .module = THIS_MODULE,
- .data = (void *)nla,
- };
-
- return nft_netlink_dump_start_rcu(info->sk, skb, info->nlh, &c);
- }
-
if (!nla[NFTA_OBJ_NAME] ||
!nla[NFTA_OBJ_TYPE])
- return -EINVAL;
+ return ERR_PTR(-EINVAL);
table = nft_table_lookup(net, nla[NFTA_OBJ_TABLE], family, genmask, 0);
if (IS_ERR(table)) {
NL_SET_BAD_ATTR(extack, nla[NFTA_OBJ_TABLE]);
- return PTR_ERR(table);
+ return ERR_CAST(table);
}
objtype = ntohl(nla_get_be32(nla[NFTA_OBJ_TYPE]));
obj = nft_obj_lookup(net, table, nla[NFTA_OBJ_NAME], objtype, genmask);
if (IS_ERR(obj)) {
NL_SET_BAD_ATTR(extack, nla[NFTA_OBJ_NAME]);
- return PTR_ERR(obj);
+ return ERR_CAST(obj);
}
skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_ATOMIC);
if (!skb2)
- return -ENOMEM;
+ return ERR_PTR(-ENOMEM);
- if (NFNL_MSG_TYPE(info->nlh->nlmsg_type) == NFT_MSG_GETOBJ_RESET)
- reset = true;
+ err = nf_tables_fill_obj_info(skb2, net, portid,
+ info->nlh->nlmsg_seq, NFT_MSG_NEWOBJ, 0,
+ family, table, obj, reset);
+ if (err < 0) {
+ kfree_skb(skb2);
+ return ERR_PTR(err);
+ }
- if (reset) {
- const struct nftables_pernet *nft_net;
- char *buf;
+ return skb2;
+}
- nft_net = nft_pernet(net);
- buf = kasprintf(GFP_ATOMIC, "%s:%u", table->name, nft_net->base_seq);
+static int nf_tables_getobj(struct sk_buff *skb, const struct nfnl_info *info,
+ const struct nlattr * const nla[])
+{
+ u32 portid = NETLINK_CB(skb).portid;
+ struct sk_buff *skb2;
- audit_log_nfcfg(buf,
- family,
- 1,
- AUDIT_NFT_OP_OBJ_RESET,
- GFP_ATOMIC);
- kfree(buf);
+ if (info->nlh->nlmsg_flags & NLM_F_DUMP) {
+ struct netlink_dump_control c = {
+ .start = nf_tables_dump_obj_start,
+ .dump = nf_tables_dump_obj,
+ .done = nf_tables_dump_obj_done,
+ .module = THIS_MODULE,
+ .data = (void *)nla,
+ };
+
+ return nft_netlink_dump_start_rcu(info->sk, skb, info->nlh, &c);
}
- err = nf_tables_fill_obj_info(skb2, net, NETLINK_CB(skb).portid,
- info->nlh->nlmsg_seq, NFT_MSG_NEWOBJ, 0,
- family, table, obj, reset);
- if (err < 0)
- goto err_fill_obj_info;
+ skb2 = nf_tables_getobj_single(portid, info, nla, false);
+ if (IS_ERR(skb2))
+ return PTR_ERR(skb2);
- return nfnetlink_unicast(skb2, net, NETLINK_CB(skb).portid);
+ return nfnetlink_unicast(skb2, info->net, portid);
+}
-err_fill_obj_info:
- kfree_skb(skb2);
- return err;
+static int nf_tables_getobj_reset(struct sk_buff *skb,
+ const struct nfnl_info *info,
+ const struct nlattr * const nla[])
+{
+ struct nftables_pernet *nft_net = nft_pernet(info->net);
+ u32 portid = NETLINK_CB(skb).portid;
+ struct net *net = info->net;
+ struct sk_buff *skb2;
+ char *buf;
+
+ if (info->nlh->nlmsg_flags & NLM_F_DUMP) {
+ struct netlink_dump_control c = {
+ .start = nf_tables_dumpreset_obj_start,
+ .dump = nf_tables_dumpreset_obj,
+ .done = nf_tables_dump_obj_done,
+ .module = THIS_MODULE,
+ .data = (void *)nla,
+ };
+
+ return nft_netlink_dump_start_rcu(info->sk, skb, info->nlh, &c);
+ }
+
+ if (!try_module_get(THIS_MODULE))
+ return -EINVAL;
+ rcu_read_unlock();
+ mutex_lock(&nft_net->commit_mutex);
+ skb2 = nf_tables_getobj_single(portid, info, nla, true);
+ mutex_unlock(&nft_net->commit_mutex);
+ rcu_read_lock();
+ module_put(THIS_MODULE);
+
+ if (IS_ERR(skb2))
+ return PTR_ERR(skb2);
+
+ buf = kasprintf(GFP_ATOMIC, "%.*s:%u",
+ nla_len(nla[NFTA_OBJ_TABLE]),
+ (char *)nla_data(nla[NFTA_OBJ_TABLE]),
+ nft_net->base_seq);
+ audit_log_nfcfg(buf, info->nfmsg->nfgen_family, 1,
+ AUDIT_NFT_OP_OBJ_RESET, GFP_ATOMIC);
+ kfree(buf);
+
+ return nfnetlink_unicast(skb2, net, portid);
}
static void nft_obj_destroy(const struct nft_ctx *ctx, struct nft_object *obj)
@@ -9410,7 +9467,7 @@ static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = {
.policy = nft_obj_policy,
},
[NFT_MSG_GETOBJ_RESET] = {
- .call = nf_tables_getobj,
+ .call = nf_tables_getobj_reset,
.type = NFNL_CB_RCU,
.attr_count = NFTA_OBJ_MAX,
.policy = nft_obj_policy,
diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c
index 4abf660c7baf..932b3ddb34f1 100644
--- a/net/netfilter/nfnetlink.c
+++ b/net/netfilter/nfnetlink.c
@@ -427,8 +427,10 @@ replay_abort:
nfnl_unlock(subsys_id);
- if (nlh->nlmsg_flags & NLM_F_ACK)
+ if (nlh->nlmsg_flags & NLM_F_ACK) {
+ memset(&extack, 0, sizeof(extack));
nfnl_err_add(&err_list, nlh, 0, &extack);
+ }
while (skb->len >= nlmsg_total_size(0)) {
int msglen, type;
@@ -577,6 +579,7 @@ done:
ss->abort(net, oskb, NFNL_ABORT_NONE);
netlink_ack(oskb, nlmsg_hdr(oskb), err, NULL);
} else if (nlh->nlmsg_flags & NLM_F_ACK) {
+ memset(&extack, 0, sizeof(extack));
nfnl_err_add(&err_list, nlh, 0, &extack);
}
} else {
diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c
index 55e28e1da66e..e0716da256bf 100644
--- a/net/netfilter/nfnetlink_queue.c
+++ b/net/netfilter/nfnetlink_queue.c
@@ -820,10 +820,41 @@ static bool nf_ct_drop_unconfirmed(const struct nf_queue_entry *entry)
{
#if IS_ENABLED(CONFIG_NF_CONNTRACK)
static const unsigned long flags = IPS_CONFIRMED | IPS_DYING;
- const struct nf_conn *ct = (void *)skb_nfct(entry->skb);
+ struct nf_conn *ct = (void *)skb_nfct(entry->skb);
+ unsigned long status;
+ unsigned int use;
- if (ct && ((ct->status & flags) == IPS_DYING))
+ if (!ct)
+ return false;
+
+ status = READ_ONCE(ct->status);
+ if ((status & flags) == IPS_DYING)
return true;
+
+ if (status & IPS_CONFIRMED)
+ return false;
+
+ /* in some cases skb_clone() can occur after initial conntrack
+ * pickup, but conntrack assumes exclusive skb->_nfct ownership for
+ * unconfirmed entries.
+ *
+ * This happens for br_netfilter and with ip multicast routing.
+ * We can't be solved with serialization here because one clone could
+ * have been queued for local delivery.
+ */
+ use = refcount_read(&ct->ct_general.use);
+ if (likely(use == 1))
+ return false;
+
+ /* Can't decrement further? Exclusive ownership. */
+ if (!refcount_dec_not_one(&ct->ct_general.use))
+ return false;
+
+ skb_set_nfct(entry->skb, 0);
+ /* No nf_ct_put(): we already decremented .use and it cannot
+ * drop down to 0.
+ */
+ return true;
#endif
return false;
}
diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c
index 113b907da0f7..3ba8e7e739b5 100644
--- a/net/sched/act_ct.c
+++ b/net/sched/act_ct.c
@@ -44,6 +44,8 @@ static DEFINE_MUTEX(zones_mutex);
struct zones_ht_key {
struct net *net;
u16 zone;
+ /* Note : pad[] must be the last field. */
+ u8 pad[];
};
struct tcf_ct_flow_table {
@@ -60,7 +62,7 @@ struct tcf_ct_flow_table {
static const struct rhashtable_params zones_params = {
.head_offset = offsetof(struct tcf_ct_flow_table, node),
.key_offset = offsetof(struct tcf_ct_flow_table, key),
- .key_len = sizeof_field(struct tcf_ct_flow_table, key),
+ .key_len = offsetof(struct zones_ht_key, pad),
.automatic_shrinking = true,
};
diff --git a/net/sctp/input.c b/net/sctp/input.c
index 17fcaa9b0df9..a8a254a5008e 100644
--- a/net/sctp/input.c
+++ b/net/sctp/input.c
@@ -735,15 +735,19 @@ static int __sctp_hash_endpoint(struct sctp_endpoint *ep)
struct sock *sk = ep->base.sk;
struct net *net = sock_net(sk);
struct sctp_hashbucket *head;
+ int err = 0;
ep->hashent = sctp_ep_hashfn(net, ep->base.bind_addr.port);
head = &sctp_ep_hashtable[ep->hashent];
+ write_lock(&head->lock);
if (sk->sk_reuseport) {
bool any = sctp_is_ep_boundall(sk);
struct sctp_endpoint *ep2;
struct list_head *list;
- int cnt = 0, err = 1;
+ int cnt = 0;
+
+ err = 1;
list_for_each(list, &ep->base.bind_addr.address_list)
cnt++;
@@ -761,24 +765,24 @@ static int __sctp_hash_endpoint(struct sctp_endpoint *ep)
if (!err) {
err = reuseport_add_sock(sk, sk2, any);
if (err)
- return err;
+ goto out;
break;
} else if (err < 0) {
- return err;
+ goto out;
}
}
if (err) {
err = reuseport_alloc(sk, any);
if (err)
- return err;
+ goto out;
}
}
- write_lock(&head->lock);
hlist_add_head(&ep->node, &head->chain);
+out:
write_unlock(&head->lock);
- return 0;
+ return err;
}
/* Add an endpoint to the hash. Local BH-safe. */
@@ -803,10 +807,9 @@ static void __sctp_unhash_endpoint(struct sctp_endpoint *ep)
head = &sctp_ep_hashtable[ep->hashent];
+ write_lock(&head->lock);
if (rcu_access_pointer(sk->sk_reuseport_cb))
reuseport_detach_sock(sk);
-
- write_lock(&head->lock);
hlist_del_init(&ep->node);
write_unlock(&head->lock);
}
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 73a875573e7a..8e3093938cd2 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -3319,10 +3319,8 @@ int smc_create_clcsk(struct net *net, struct sock *sk, int family)
rc = sock_create_kern(net, family, SOCK_STREAM, IPPROTO_TCP,
&smc->clcsock);
- if (rc) {
- sk_common_release(sk);
+ if (rc)
return rc;
- }
/* smc_clcsock_release() does not wait smc->clcsock->sk's
* destruction; its sk_state might not be TCP_CLOSE after
@@ -3368,6 +3366,9 @@ static int __smc_create(struct net *net, struct socket *sock, int protocol,
smc->clcsock = clcsock;
else
rc = smc_create_clcsk(net, sk, family);
+
+ if (rc)
+ sk_common_release(sk);
out:
return rc;
}
diff --git a/net/smc/smc_stats.h b/net/smc/smc_stats.h
index 9d32058db2b5..e19177ce4092 100644
--- a/net/smc/smc_stats.h
+++ b/net/smc/smc_stats.h
@@ -19,7 +19,7 @@
#include "smc_clc.h"
-#define SMC_MAX_FBACK_RSN_CNT 30
+#define SMC_MAX_FBACK_RSN_CNT 36
enum {
SMC_BUF_8K,
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index e03f14024e47..88a59cfa5583 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -161,7 +161,7 @@ param_get_pool_mode(char *buf, const struct kernel_param *kp)
str[len] = '\n';
str[len + 1] = '\0';
- return sysfs_emit(buf, str);
+ return sysfs_emit(buf, "%s", str);
}
module_param_call(pool_mode, param_set_pool_mode, param_get_pool_mode,
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index 4b040285aa78..0ff9b2dd86ba 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -1270,25 +1270,28 @@ out:
return err;
}
+int __vsock_dgram_recvmsg(struct socket *sock, struct msghdr *msg,
+ size_t len, int flags)
+{
+ struct sock *sk = sock->sk;
+ struct vsock_sock *vsk = vsock_sk(sk);
+
+ return vsk->transport->dgram_dequeue(vsk, msg, len, flags);
+}
+
int vsock_dgram_recvmsg(struct socket *sock, struct msghdr *msg,
size_t len, int flags)
{
#ifdef CONFIG_BPF_SYSCALL
+ struct sock *sk = sock->sk;
const struct proto *prot;
-#endif
- struct vsock_sock *vsk;
- struct sock *sk;
- sk = sock->sk;
- vsk = vsock_sk(sk);
-
-#ifdef CONFIG_BPF_SYSCALL
prot = READ_ONCE(sk->sk_prot);
if (prot != &vsock_proto)
return prot->recvmsg(sk, msg, len, flags, NULL);
#endif
- return vsk->transport->dgram_dequeue(vsk, msg, len, flags);
+ return __vsock_dgram_recvmsg(sock, msg, len, flags);
}
EXPORT_SYMBOL_GPL(vsock_dgram_recvmsg);
@@ -2174,15 +2177,12 @@ out:
}
int
-vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
- int flags)
+__vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
+ int flags)
{
struct sock *sk;
struct vsock_sock *vsk;
const struct vsock_transport *transport;
-#ifdef CONFIG_BPF_SYSCALL
- const struct proto *prot;
-#endif
int err;
sk = sock->sk;
@@ -2233,14 +2233,6 @@ vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
goto out;
}
-#ifdef CONFIG_BPF_SYSCALL
- prot = READ_ONCE(sk->sk_prot);
- if (prot != &vsock_proto) {
- release_sock(sk);
- return prot->recvmsg(sk, msg, len, flags, NULL);
- }
-#endif
-
if (sk->sk_type == SOCK_STREAM)
err = __vsock_stream_recvmsg(sk, msg, len, flags);
else
@@ -2250,6 +2242,22 @@ out:
release_sock(sk);
return err;
}
+
+int
+vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
+ int flags)
+{
+#ifdef CONFIG_BPF_SYSCALL
+ struct sock *sk = sock->sk;
+ const struct proto *prot;
+
+ prot = READ_ONCE(sk->sk_prot);
+ if (prot != &vsock_proto)
+ return prot->recvmsg(sk, msg, len, flags, NULL);
+#endif
+
+ return __vsock_connectible_recvmsg(sock, msg, len, flags);
+}
EXPORT_SYMBOL_GPL(vsock_connectible_recvmsg);
static int vsock_set_rcvlowat(struct sock *sk, int val)
diff --git a/net/vmw_vsock/vsock_bpf.c b/net/vmw_vsock/vsock_bpf.c
index a3c97546ab84..c42c5cc18f32 100644
--- a/net/vmw_vsock/vsock_bpf.c
+++ b/net/vmw_vsock/vsock_bpf.c
@@ -64,9 +64,9 @@ static int __vsock_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int
int err;
if (sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET)
- err = vsock_connectible_recvmsg(sock, msg, len, flags);
+ err = __vsock_connectible_recvmsg(sock, msg, len, flags);
else if (sk->sk_type == SOCK_DGRAM)
- err = vsock_dgram_recvmsg(sock, msg, len, flags);
+ err = __vsock_dgram_recvmsg(sock, msg, len, flags);
else
err = -EPROTOTYPE;
diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index d99319d82205..64eeed82d43d 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -3178,8 +3178,7 @@ cfg80211_inform_bss_frame_data(struct wiphy *wiphy,
struct ieee80211_mgmt *mgmt, size_t len,
gfp_t gfp)
{
- size_t min_hdr_len = offsetof(struct ieee80211_mgmt,
- u.probe_resp.variable);
+ size_t min_hdr_len;
struct ieee80211_ext *ext = NULL;
enum cfg80211_bss_frame_type ftype;
u16 beacon_interval;
@@ -3202,10 +3201,16 @@ cfg80211_inform_bss_frame_data(struct wiphy *wiphy,
if (ieee80211_is_s1g_beacon(mgmt->frame_control)) {
ext = (void *) mgmt;
- min_hdr_len = offsetof(struct ieee80211_ext, u.s1g_beacon);
if (ieee80211_is_s1g_short_beacon(mgmt->frame_control))
min_hdr_len = offsetof(struct ieee80211_ext,
u.s1g_short_beacon.variable);
+ else
+ min_hdr_len = offsetof(struct ieee80211_ext,
+ u.s1g_beacon.variable);
+ } else {
+ /* same for beacons */
+ min_hdr_len = offsetof(struct ieee80211_mgmt,
+ u.probe_resp.variable);
}
if (WARN_ON(len < min_hdr_len))
diff --git a/net/wireless/sme.c b/net/wireless/sme.c
index e419aa8c4a5a..d9d7bf8bb5c1 100644
--- a/net/wireless/sme.c
+++ b/net/wireless/sme.c
@@ -1045,6 +1045,7 @@ void cfg80211_connect_done(struct net_device *dev,
cfg80211_hold_bss(
bss_from_pub(params->links[link].bss));
ev->cr.links[link].bss = params->links[link].bss;
+ ev->cr.links[link].status = params->links[link].status;
if (params->links[link].addr) {
ev->cr.links[link].addr = next;