summaryrefslogtreecommitdiff
path: root/net/core
diff options
context:
space:
mode:
Diffstat (limited to 'net/core')
-rw-r--r--net/core/dev.c37
-rw-r--r--net/core/dev_api.c23
-rw-r--r--net/core/fib_rules.c48
-rw-r--r--net/core/filter.c1
-rw-r--r--net/core/lwtunnel.c26
-rw-r--r--net/core/netdev-genl.c78
-rw-r--r--net/core/rtnetlink.c5
-rw-r--r--net/core/selftests.c18
8 files changed, 173 insertions, 63 deletions
diff --git a/net/core/dev.c b/net/core/dev.c
index 75e104322ad5..11da1e272ec2 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1520,6 +1520,8 @@ EXPORT_SYMBOL(netdev_features_change);
void netif_state_change(struct net_device *dev)
{
+ netdev_ops_assert_locked_or_invisible(dev);
+
if (dev->flags & IFF_UP) {
struct netdev_notifier_change_info change_info = {
.info.dev = dev,
@@ -9191,18 +9193,7 @@ static int __dev_set_promiscuity(struct net_device *dev, int inc, bool notify)
return 0;
}
-/**
- * dev_set_promiscuity - update promiscuity count on a device
- * @dev: device
- * @inc: modifier
- *
- * Add or remove promiscuity from a device. While the count in the device
- * remains above zero the interface remains promiscuous. Once it hits zero
- * the device reverts back to normal filtering operation. A negative inc
- * value is used to drop promiscuity on the device.
- * Return 0 if successful or a negative errno code on error.
- */
-int dev_set_promiscuity(struct net_device *dev, int inc)
+int netif_set_promiscuity(struct net_device *dev, int inc)
{
unsigned int old_flags = dev->flags;
int err;
@@ -9214,7 +9205,6 @@ int dev_set_promiscuity(struct net_device *dev, int inc)
dev_set_rx_mode(dev);
return err;
}
-EXPORT_SYMBOL(dev_set_promiscuity);
int netif_set_allmulti(struct net_device *dev, int inc, bool notify)
{
@@ -11932,15 +11922,24 @@ void unregister_netdevice_many_notify(struct list_head *head,
BUG_ON(dev->reg_state != NETREG_REGISTERED);
}
- /* If device is running, close it first. */
+ /* If device is running, close it first. Start with ops locked... */
list_for_each_entry(dev, head, unreg_list) {
- list_add_tail(&dev->close_list, &close_head);
- netdev_lock_ops(dev);
+ if (netdev_need_ops_lock(dev)) {
+ list_add_tail(&dev->close_list, &close_head);
+ netdev_lock(dev);
+ }
+ }
+ dev_close_many(&close_head, true);
+ /* ... now unlock them and go over the rest. */
+ list_for_each_entry(dev, head, unreg_list) {
+ if (netdev_need_ops_lock(dev))
+ netdev_unlock(dev);
+ else
+ list_add_tail(&dev->close_list, &close_head);
}
dev_close_many(&close_head, true);
list_for_each_entry(dev, head, unreg_list) {
- netdev_unlock_ops(dev);
/* And unlink it from device chain. */
unlist_netdevice(dev);
netdev_lock(dev);
@@ -11955,9 +11954,9 @@ void unregister_netdevice_many_notify(struct list_head *head,
struct sk_buff *skb = NULL;
/* Shutdown queueing discipline. */
+ netdev_lock_ops(dev);
dev_shutdown(dev);
dev_tcx_uninstall(dev);
- netdev_lock_ops(dev);
dev_xdp_uninstall(dev);
dev_memory_provider_uninstall(dev);
netdev_unlock_ops(dev);
@@ -12150,7 +12149,9 @@ int __dev_change_net_namespace(struct net_device *dev, struct net *net,
synchronize_net();
/* Shutdown queueing discipline. */
+ netdev_lock_ops(dev);
dev_shutdown(dev);
+ netdev_unlock_ops(dev);
/* Notify protocols, that we are about to destroy
* this device. They should clean all the things.
diff --git a/net/core/dev_api.c b/net/core/dev_api.c
index 90898cd540ce..f9a160ab596f 100644
--- a/net/core/dev_api.c
+++ b/net/core/dev_api.c
@@ -268,6 +268,29 @@ void dev_disable_lro(struct net_device *dev)
EXPORT_SYMBOL(dev_disable_lro);
/**
+ * dev_set_promiscuity() - update promiscuity count on a device
+ * @dev: device
+ * @inc: modifier
+ *
+ * Add or remove promiscuity from a device. While the count in the device
+ * remains above zero the interface remains promiscuous. Once it hits zero
+ * the device reverts back to normal filtering operation. A negative inc
+ * value is used to drop promiscuity on the device.
+ * Return 0 if successful or a negative errno code on error.
+ */
+int dev_set_promiscuity(struct net_device *dev, int inc)
+{
+ int ret;
+
+ netdev_lock_ops(dev);
+ ret = netif_set_promiscuity(dev, inc);
+ netdev_unlock_ops(dev);
+
+ return ret;
+}
+EXPORT_SYMBOL(dev_set_promiscuity);
+
+/**
* dev_set_allmulti() - update allmulti count on a device
* @dev: device
* @inc: modifier
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index 4bc64d912a1c..7af302080a66 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -257,6 +257,24 @@ static int nla_put_port_range(struct sk_buff *skb, int attrtype,
return nla_put(skb, attrtype, sizeof(*range), range);
}
+static bool fib_rule_iif_match(const struct fib_rule *rule, int iifindex,
+ const struct flowi *fl)
+{
+ u8 iif_is_l3_master = READ_ONCE(rule->iif_is_l3_master);
+
+ return iif_is_l3_master ? l3mdev_fib_rule_iif_match(fl, iifindex) :
+ fl->flowi_iif == iifindex;
+}
+
+static bool fib_rule_oif_match(const struct fib_rule *rule, int oifindex,
+ const struct flowi *fl)
+{
+ u8 oif_is_l3_master = READ_ONCE(rule->oif_is_l3_master);
+
+ return oif_is_l3_master ? l3mdev_fib_rule_oif_match(fl, oifindex) :
+ fl->flowi_oif == oifindex;
+}
+
static int fib_rule_match(struct fib_rule *rule, struct fib_rules_ops *ops,
struct flowi *fl, int flags,
struct fib_lookup_arg *arg)
@@ -264,11 +282,11 @@ static int fib_rule_match(struct fib_rule *rule, struct fib_rules_ops *ops,
int iifindex, oifindex, ret = 0;
iifindex = READ_ONCE(rule->iifindex);
- if (iifindex && (iifindex != fl->flowi_iif))
+ if (iifindex && !fib_rule_iif_match(rule, iifindex, fl))
goto out;
oifindex = READ_ONCE(rule->oifindex);
- if (oifindex && (oifindex != fl->flowi_oif))
+ if (oifindex && !fib_rule_oif_match(rule, oifindex, fl))
goto out;
if ((rule->mark ^ fl->flowi_mark) & rule->mark_mask)
@@ -736,16 +754,20 @@ static int fib_nl2rule_rtnl(struct fib_rule *nlrule,
struct net_device *dev;
dev = __dev_get_by_name(nlrule->fr_net, nlrule->iifname);
- if (dev)
+ if (dev) {
nlrule->iifindex = dev->ifindex;
+ nlrule->iif_is_l3_master = netif_is_l3_master(dev);
+ }
}
if (tb[FRA_OIFNAME]) {
struct net_device *dev;
dev = __dev_get_by_name(nlrule->fr_net, nlrule->oifname);
- if (dev)
+ if (dev) {
nlrule->oifindex = dev->ifindex;
+ nlrule->oif_is_l3_master = netif_is_l3_master(dev);
+ }
}
return 0;
@@ -1336,11 +1358,17 @@ static void attach_rules(struct list_head *rules, struct net_device *dev)
list_for_each_entry(rule, rules, list) {
if (rule->iifindex == -1 &&
- strcmp(dev->name, rule->iifname) == 0)
+ strcmp(dev->name, rule->iifname) == 0) {
WRITE_ONCE(rule->iifindex, dev->ifindex);
+ WRITE_ONCE(rule->iif_is_l3_master,
+ netif_is_l3_master(dev));
+ }
if (rule->oifindex == -1 &&
- strcmp(dev->name, rule->oifname) == 0)
+ strcmp(dev->name, rule->oifname) == 0) {
WRITE_ONCE(rule->oifindex, dev->ifindex);
+ WRITE_ONCE(rule->oif_is_l3_master,
+ netif_is_l3_master(dev));
+ }
}
}
@@ -1349,10 +1377,14 @@ static void detach_rules(struct list_head *rules, struct net_device *dev)
struct fib_rule *rule;
list_for_each_entry(rule, rules, list) {
- if (rule->iifindex == dev->ifindex)
+ if (rule->iifindex == dev->ifindex) {
WRITE_ONCE(rule->iifindex, -1);
- if (rule->oifindex == dev->ifindex)
+ WRITE_ONCE(rule->iif_is_l3_master, false);
+ }
+ if (rule->oifindex == dev->ifindex) {
WRITE_ONCE(rule->oifindex, -1);
+ WRITE_ONCE(rule->oif_is_l3_master, false);
+ }
}
}
diff --git a/net/core/filter.c b/net/core/filter.c
index 79cab4d78dc3..577a4504e26f 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2509,6 +2509,7 @@ int skb_do_redirect(struct sk_buff *skb)
goto out_drop;
skb->dev = dev;
dev_sw_netstats_rx_add(dev, skb->len);
+ skb_scrub_packet(skb, false);
return -EAGAIN;
}
return flags & BPF_F_NEIGH ?
diff --git a/net/core/lwtunnel.c b/net/core/lwtunnel.c
index e39a459540ec..60f27cb4e54f 100644
--- a/net/core/lwtunnel.c
+++ b/net/core/lwtunnel.c
@@ -333,6 +333,8 @@ int lwtunnel_output(struct net *net, struct sock *sk, struct sk_buff *skb)
struct dst_entry *dst;
int ret;
+ local_bh_disable();
+
if (dev_xmit_recursion()) {
net_crit_ratelimited("%s(): recursion limit reached on datapath\n",
__func__);
@@ -348,8 +350,10 @@ int lwtunnel_output(struct net *net, struct sock *sk, struct sk_buff *skb)
lwtstate = dst->lwtstate;
if (lwtstate->type == LWTUNNEL_ENCAP_NONE ||
- lwtstate->type > LWTUNNEL_ENCAP_MAX)
- return 0;
+ lwtstate->type > LWTUNNEL_ENCAP_MAX) {
+ ret = 0;
+ goto out;
+ }
ret = -EOPNOTSUPP;
rcu_read_lock();
@@ -364,11 +368,13 @@ int lwtunnel_output(struct net *net, struct sock *sk, struct sk_buff *skb)
if (ret == -EOPNOTSUPP)
goto drop;
- return ret;
+ goto out;
drop:
kfree_skb(skb);
+out:
+ local_bh_enable();
return ret;
}
EXPORT_SYMBOL_GPL(lwtunnel_output);
@@ -380,6 +386,8 @@ int lwtunnel_xmit(struct sk_buff *skb)
struct dst_entry *dst;
int ret;
+ local_bh_disable();
+
if (dev_xmit_recursion()) {
net_crit_ratelimited("%s(): recursion limit reached on datapath\n",
__func__);
@@ -396,8 +404,10 @@ int lwtunnel_xmit(struct sk_buff *skb)
lwtstate = dst->lwtstate;
if (lwtstate->type == LWTUNNEL_ENCAP_NONE ||
- lwtstate->type > LWTUNNEL_ENCAP_MAX)
- return 0;
+ lwtstate->type > LWTUNNEL_ENCAP_MAX) {
+ ret = 0;
+ goto out;
+ }
ret = -EOPNOTSUPP;
rcu_read_lock();
@@ -412,11 +422,13 @@ int lwtunnel_xmit(struct sk_buff *skb)
if (ret == -EOPNOTSUPP)
goto drop;
- return ret;
+ goto out;
drop:
kfree_skb(skb);
+out:
+ local_bh_enable();
return ret;
}
EXPORT_SYMBOL_GPL(lwtunnel_xmit);
@@ -428,6 +440,8 @@ int lwtunnel_input(struct sk_buff *skb)
struct dst_entry *dst;
int ret;
+ DEBUG_NET_WARN_ON_ONCE(!in_softirq());
+
if (dev_xmit_recursion()) {
net_crit_ratelimited("%s(): recursion limit reached on datapath\n",
__func__);
diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c
index 5d7af50fe702..dae9f0d432fb 100644
--- a/net/core/netdev-genl.c
+++ b/net/core/netdev-genl.c
@@ -708,25 +708,66 @@ netdev_nl_stats_by_queue(struct net_device *netdev, struct sk_buff *rsp,
return 0;
}
+/**
+ * netdev_stat_queue_sum() - add up queue stats from range of queues
+ * @netdev: net_device
+ * @rx_start: index of the first Rx queue to query
+ * @rx_end: index after the last Rx queue (first *not* to query)
+ * @rx_sum: output Rx stats, should be already initialized
+ * @tx_start: index of the first Tx queue to query
+ * @tx_end: index after the last Tx queue (first *not* to query)
+ * @tx_sum: output Tx stats, should be already initialized
+ *
+ * Add stats from [start, end) range of queue IDs to *x_sum structs.
+ * The sum structs must be already initialized. Usually this
+ * helper is invoked from the .get_base_stats callbacks of drivers
+ * to account for stats of disabled queues. In that case the ranges
+ * are usually [netdev->real_num_*x_queues, netdev->num_*x_queues).
+ */
+void netdev_stat_queue_sum(struct net_device *netdev,
+ int rx_start, int rx_end,
+ struct netdev_queue_stats_rx *rx_sum,
+ int tx_start, int tx_end,
+ struct netdev_queue_stats_tx *tx_sum)
+{
+ const struct netdev_stat_ops *ops;
+ struct netdev_queue_stats_rx rx;
+ struct netdev_queue_stats_tx tx;
+ int i;
+
+ ops = netdev->stat_ops;
+
+ for (i = rx_start; i < rx_end; i++) {
+ memset(&rx, 0xff, sizeof(rx));
+ if (ops->get_queue_stats_rx)
+ ops->get_queue_stats_rx(netdev, i, &rx);
+ netdev_nl_stats_add(rx_sum, &rx, sizeof(rx));
+ }
+ for (i = tx_start; i < tx_end; i++) {
+ memset(&tx, 0xff, sizeof(tx));
+ if (ops->get_queue_stats_tx)
+ ops->get_queue_stats_tx(netdev, i, &tx);
+ netdev_nl_stats_add(tx_sum, &tx, sizeof(tx));
+ }
+}
+EXPORT_SYMBOL(netdev_stat_queue_sum);
+
static int
netdev_nl_stats_by_netdev(struct net_device *netdev, struct sk_buff *rsp,
const struct genl_info *info)
{
- struct netdev_queue_stats_rx rx_sum, rx;
- struct netdev_queue_stats_tx tx_sum, tx;
- const struct netdev_stat_ops *ops;
+ struct netdev_queue_stats_rx rx_sum;
+ struct netdev_queue_stats_tx tx_sum;
void *hdr;
- int i;
- ops = netdev->stat_ops;
/* Netdev can't guarantee any complete counters */
- if (!ops->get_base_stats)
+ if (!netdev->stat_ops->get_base_stats)
return 0;
memset(&rx_sum, 0xff, sizeof(rx_sum));
memset(&tx_sum, 0xff, sizeof(tx_sum));
- ops->get_base_stats(netdev, &rx_sum, &tx_sum);
+ netdev->stat_ops->get_base_stats(netdev, &rx_sum, &tx_sum);
/* The op was there, but nothing reported, don't bother */
if (!memchr_inv(&rx_sum, 0xff, sizeof(rx_sum)) &&
@@ -739,18 +780,8 @@ netdev_nl_stats_by_netdev(struct net_device *netdev, struct sk_buff *rsp,
if (nla_put_u32(rsp, NETDEV_A_QSTATS_IFINDEX, netdev->ifindex))
goto nla_put_failure;
- for (i = 0; i < netdev->real_num_rx_queues; i++) {
- memset(&rx, 0xff, sizeof(rx));
- if (ops->get_queue_stats_rx)
- ops->get_queue_stats_rx(netdev, i, &rx);
- netdev_nl_stats_add(&rx_sum, &rx, sizeof(rx));
- }
- for (i = 0; i < netdev->real_num_tx_queues; i++) {
- memset(&tx, 0xff, sizeof(tx));
- if (ops->get_queue_stats_tx)
- ops->get_queue_stats_tx(netdev, i, &tx);
- netdev_nl_stats_add(&tx_sum, &tx, sizeof(tx));
- }
+ netdev_stat_queue_sum(netdev, 0, netdev->real_num_rx_queues, &rx_sum,
+ 0, netdev->real_num_tx_queues, &tx_sum);
if (netdev_nl_stats_write_rx(rsp, &rx_sum) ||
netdev_nl_stats_write_tx(rsp, &tx_sum))
@@ -861,14 +892,17 @@ int netdev_nl_bind_rx_doit(struct sk_buff *skb, struct genl_info *info)
mutex_lock(&priv->lock);
+ err = 0;
netdev = netdev_get_by_index_lock(genl_info_net(info), ifindex);
- if (!netdev || !netif_device_present(netdev)) {
+ if (!netdev) {
err = -ENODEV;
goto err_unlock_sock;
}
-
- if (!netdev_need_ops_lock(netdev)) {
+ if (!netif_device_present(netdev))
+ err = -ENODEV;
+ else if (!netdev_need_ops_lock(netdev))
err = -EOPNOTSUPP;
+ if (err) {
NL_SET_BAD_ATTR(info->extack,
info->attrs[NETDEV_A_DEV_IFINDEX]);
goto err_unlock;
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 39a5b72e861f..c5a7f41982a5 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -3676,11 +3676,8 @@ struct net_device *rtnl_create_link(struct net *net, const char *ifname,
nla_len(tb[IFLA_BROADCAST]));
if (tb[IFLA_TXQLEN])
dev->tx_queue_len = nla_get_u32(tb[IFLA_TXQLEN]);
- if (tb[IFLA_OPERSTATE]) {
- netdev_lock_ops(dev);
+ if (tb[IFLA_OPERSTATE])
set_operstate(dev, nla_get_u8(tb[IFLA_OPERSTATE]));
- netdev_unlock_ops(dev);
- }
if (tb[IFLA_LINKMODE])
dev->link_mode = nla_get_u8(tb[IFLA_LINKMODE]);
if (tb[IFLA_GROUP])
diff --git a/net/core/selftests.c b/net/core/selftests.c
index e99ae983fca9..35f807ea9952 100644
--- a/net/core/selftests.c
+++ b/net/core/selftests.c
@@ -100,10 +100,10 @@ static struct sk_buff *net_test_get_skb(struct net_device *ndev,
ehdr->h_proto = htons(ETH_P_IP);
if (attr->tcp) {
+ memset(thdr, 0, sizeof(*thdr));
thdr->source = htons(attr->sport);
thdr->dest = htons(attr->dport);
thdr->doff = sizeof(struct tcphdr) / 4;
- thdr->check = 0;
} else {
uhdr->source = htons(attr->sport);
uhdr->dest = htons(attr->dport);
@@ -144,10 +144,18 @@ static struct sk_buff *net_test_get_skb(struct net_device *ndev,
attr->id = net_test_next_id;
shdr->id = net_test_next_id++;
- if (attr->size)
- skb_put(skb, attr->size);
- if (attr->max_size && attr->max_size > skb->len)
- skb_put(skb, attr->max_size - skb->len);
+ if (attr->size) {
+ void *payload = skb_put(skb, attr->size);
+
+ memset(payload, 0, attr->size);
+ }
+
+ if (attr->max_size && attr->max_size > skb->len) {
+ size_t pad_len = attr->max_size - skb->len;
+ void *pad = skb_put(skb, pad_len);
+
+ memset(pad, 0, pad_len);
+ }
skb->csum = 0;
skb->ip_summed = CHECKSUM_PARTIAL;
generated by cgit (git 2.34.1) at 2025-05-15 11:59:30 +0000