summaryrefslogtreecommitdiff
path: root/net/core
diff options
context:
space:
mode:
Diffstat (limited to 'net/core')
-rw-r--r--net/core/dev.c12
-rw-r--r--net/core/dev.h12
-rw-r--r--net/core/filter.c1
-rw-r--r--net/core/lwtunnel.c26
-rw-r--r--net/core/net-sysfs.c5
-rw-r--r--net/core/netdev-genl.c69
-rw-r--r--net/core/page_pool.c7
-rw-r--r--net/core/pktgen.c13
-rw-r--r--net/core/rtnetlink.c10
-rw-r--r--net/core/selftests.c18
10 files changed, 126 insertions, 47 deletions
diff --git a/net/core/dev.c b/net/core/dev.c
index 2f7f5fd9ffec..77306b522966 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -6187,16 +6187,18 @@ EXPORT_SYMBOL(netif_receive_skb_list);
static void flush_backlog(struct work_struct *work)
{
struct sk_buff *skb, *tmp;
+ struct sk_buff_head list;
struct softnet_data *sd;
+ __skb_queue_head_init(&list);
local_bh_disable();
sd = this_cpu_ptr(&softnet_data);
backlog_lock_irq_disable(sd);
skb_queue_walk_safe(&sd->input_pkt_queue, skb, tmp) {
- if (skb->dev->reg_state == NETREG_UNREGISTERING) {
+ if (READ_ONCE(skb->dev->reg_state) == NETREG_UNREGISTERING) {
__skb_unlink(skb, &sd->input_pkt_queue);
- dev_kfree_skb_irq(skb);
+ __skb_queue_tail(&list, skb);
rps_input_queue_head_incr(sd);
}
}
@@ -6204,14 +6206,16 @@ static void flush_backlog(struct work_struct *work)
local_lock_nested_bh(&softnet_data.process_queue_bh_lock);
skb_queue_walk_safe(&sd->process_queue, skb, tmp) {
- if (skb->dev->reg_state == NETREG_UNREGISTERING) {
+ if (READ_ONCE(skb->dev->reg_state) == NETREG_UNREGISTERING) {
__skb_unlink(skb, &sd->process_queue);
- kfree_skb(skb);
+ __skb_queue_tail(&list, skb);
rps_input_queue_head_incr(sd);
}
}
local_unlock_nested_bh(&softnet_data.process_queue_bh_lock);
local_bh_enable();
+
+ __skb_queue_purge_reason(&list, SKB_DROP_REASON_DEV_READY);
}
static bool flush_required(int cpu)
diff --git a/net/core/dev.h b/net/core/dev.h
index a5b166bbd169..caa13e431a6b 100644
--- a/net/core/dev.h
+++ b/net/core/dev.h
@@ -299,6 +299,18 @@ void xdp_do_check_flushed(struct napi_struct *napi);
static inline void xdp_do_check_flushed(struct napi_struct *napi) { }
#endif
+/* Best effort check that NAPI is not idle (can't be scheduled to run) */
+static inline void napi_assert_will_not_race(const struct napi_struct *napi)
+{
+ /* uninitialized instance, can't race */
+ if (!napi->poll_list.next)
+ return;
+
+ /* SCHED bit is set on disabled instances */
+ WARN_ON(!test_bit(NAPI_STATE_SCHED, &napi->state));
+ WARN_ON(READ_ONCE(napi->list_owner) != -1);
+}
+
void kick_defer_list_purge(struct softnet_data *sd, unsigned int cpu);
#define XMIT_RECURSION_LIMIT 8
diff --git a/net/core/filter.c b/net/core/filter.c
index b0df9b7d16d3..6c8fbc96b14a 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 4417a18b3e95..f63586c9ce02 100644
--- a/net/core/lwtunnel.c
+++ b/net/core/lwtunnel.c
@@ -332,6 +332,8 @@ 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__);
@@ -347,8 +349,10 @@ 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();
@@ -363,11 +367,13 @@ 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);
@@ -379,6 +385,8 @@ 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__);
@@ -395,8 +403,10 @@ 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();
@@ -411,11 +421,13 @@ 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);
@@ -427,6 +439,8 @@ 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/net-sysfs.c b/net/core/net-sysfs.c
index 07cb99b114bd..88e001a4e081 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -232,11 +232,12 @@ static ssize_t carrier_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct net_device *netdev = to_net_dev(dev);
- int ret = -EINVAL;
+ int ret;
if (!rtnl_trylock())
return restart_syscall();
+ ret = -EINVAL;
if (netif_running(netdev)) {
/* Synchronize carrier state with link watch,
* see also rtnl_getlink().
@@ -266,6 +267,7 @@ static ssize_t speed_show(struct device *dev,
if (!rtnl_trylock())
return restart_syscall();
+ ret = -EINVAL;
if (netif_running(netdev)) {
struct ethtool_link_ksettings cmd;
@@ -292,6 +294,7 @@ static ssize_t duplex_show(struct device *dev,
if (!rtnl_trylock())
return restart_syscall();
+ ret = -EINVAL;
if (netif_running(netdev)) {
struct ethtool_link_ksettings cmd;
diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c
index 7832abc5ca6e..9be2bdd2dca8 100644
--- a/net/core/netdev-genl.c
+++ b/net/core/netdev-genl.c
@@ -690,25 +690,66 @@ 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)) &&
@@ -721,18 +762,8 @@ 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))
diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index ede82c610936..cca51aa2e876 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -25,6 +25,7 @@
#include <trace/events/page_pool.h>
+#include "dev.h"
#include "mp_dmabuf_devmem.h"
#include "netmem_priv.h"
#include "page_pool_priv.h"
@@ -1146,11 +1147,7 @@ void page_pool_disable_direct_recycling(struct page_pool *pool)
if (!pool->p.napi)
return;
- /* To avoid races with recycling and additional barriers make sure
- * pool and NAPI are unlinked when NAPI is disabled.
- */
- WARN_ON(!test_bit(NAPI_STATE_SCHED, &pool->p.napi->state));
- WARN_ON(READ_ONCE(pool->p.napi->list_owner) != -1);
+ napi_assert_will_not_race(pool->p.napi);
mutex_lock(&page_pools_lock);
WRITE_ONCE(pool->p.napi, NULL);
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 82b6a2c3c141..d3a76e81dd88 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -898,6 +898,10 @@ static ssize_t get_labels(const char __user *buffer, struct pktgen_dev *pkt_dev)
pkt_dev->nr_labels = 0;
do {
__u32 tmp;
+
+ if (n >= MAX_MPLS_LABELS)
+ return -E2BIG;
+
len = hex32_arg(&buffer[i], 8, &tmp);
if (len <= 0)
return len;
@@ -909,8 +913,6 @@ static ssize_t get_labels(const char __user *buffer, struct pktgen_dev *pkt_dev)
return -EFAULT;
i++;
n++;
- if (n >= MAX_MPLS_LABELS)
- return -E2BIG;
} while (c == ',');
pkt_dev->nr_labels = n;
@@ -1896,8 +1898,8 @@ static ssize_t pktgen_thread_write(struct file *file,
i = len;
/* Read variable name */
-
- len = strn_len(&user_buffer[i], sizeof(name) - 1);
+ max = min(sizeof(name) - 1, count - i);
+ len = strn_len(&user_buffer[i], max);
if (len < 0)
return len;
@@ -1927,7 +1929,8 @@ static ssize_t pktgen_thread_write(struct file *file,
if (!strcmp(name, "add_device")) {
char f[32];
memset(f, 0, 32);
- len = strn_len(&user_buffer[i], sizeof(f) - 1);
+ max = min(sizeof(f) - 1, count - i);
+ len = strn_len(&user_buffer[i], max);
if (len < 0) {
ret = len;
goto out;
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 80e006940f51..ab7041150f29 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -3865,20 +3865,26 @@ static int __rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh,
{
struct nlattr ** const tb = tbs->tb;
struct net *net = sock_net(skb->sk);
+ struct net *device_net;
struct net_device *dev;
struct ifinfomsg *ifm;
bool link_specified;
+ /* When creating, lookup for existing device in target net namespace */
+ device_net = (nlh->nlmsg_flags & NLM_F_CREATE) &&
+ (nlh->nlmsg_flags & NLM_F_EXCL) ?
+ tgt_net : net;
+
ifm = nlmsg_data(nlh);
if (ifm->ifi_index > 0) {
link_specified = true;
- dev = __dev_get_by_index(net, ifm->ifi_index);
+ dev = __dev_get_by_index(device_net, ifm->ifi_index);
} else if (ifm->ifi_index < 0) {
NL_SET_ERR_MSG(extack, "ifindex can't be negative");
return -EINVAL;
} else if (tb[IFLA_IFNAME] || tb[IFLA_ALT_IFNAME]) {
link_specified = true;
- dev = rtnl_dev_get(net, tb);
+ dev = rtnl_dev_get(device_net, tb);
} else {
link_specified = false;
dev = NULL;
diff --git a/net/core/selftests.c b/net/core/selftests.c
index 8f801e6e3b91..561653f9d71d 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 v1.2.3 (git 2.39.0) at 2025-07-06 14:49:09 +0300