aboutsummaryrefslogtreecommitdiff
path: root/net/core
diff options
context:
space:
mode:
Diffstat (limited to 'net/core')
-rw-r--r--net/core/dev.c64
-rw-r--r--net/core/drop_monitor.c4
-rw-r--r--net/core/filter.c38
-rw-r--r--net/core/gso_test.c14
-rw-r--r--net/core/neighbour.c9
-rw-r--r--net/core/scm.c8
-rw-r--r--net/core/skbuff.c5
-rw-r--r--net/core/skmsg.c2
-rw-r--r--net/core/sock.c12
-rw-r--r--net/core/sock_map.c2
-rw-r--r--net/core/stream.c2
11 files changed, 137 insertions, 23 deletions
diff --git a/net/core/dev.c b/net/core/dev.c
index 0d548431f3fa..ad20bebe153f 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1119,7 +1119,9 @@ static int __dev_alloc_name(struct net *net, const char *name, char *res)
if (i == max_netdevices)
return -ENFILE;
- snprintf(res, IFNAMSIZ, name, i);
+ /* 'res' and 'name' could overlap, use 'buf' as an intermediate buffer */
+ strscpy(buf, name, IFNAMSIZ);
+ snprintf(res, IFNAMSIZ, buf, i);
return i;
}
@@ -3470,6 +3472,9 @@ static netdev_features_t gso_features_check(const struct sk_buff *skb,
if (gso_segs > READ_ONCE(dev->gso_max_segs))
return features & ~NETIF_F_GSO_MASK;
+ if (unlikely(skb->len >= READ_ONCE(dev->gso_max_size)))
+ return features & ~NETIF_F_GSO_MASK;
+
if (!skb_shinfo(skb)->gso_type) {
skb_warn_bad_offload(skb);
return features & ~NETIF_F_GSO_MASK;
@@ -10049,6 +10054,54 @@ void netif_tx_stop_all_queues(struct net_device *dev)
}
EXPORT_SYMBOL(netif_tx_stop_all_queues);
+static int netdev_do_alloc_pcpu_stats(struct net_device *dev)
+{
+ void __percpu *v;
+
+ /* Drivers implementing ndo_get_peer_dev must support tstat
+ * accounting, so that skb_do_redirect() can bump the dev's
+ * RX stats upon network namespace switch.
+ */
+ if (dev->netdev_ops->ndo_get_peer_dev &&
+ dev->pcpu_stat_type != NETDEV_PCPU_STAT_TSTATS)
+ return -EOPNOTSUPP;
+
+ switch (dev->pcpu_stat_type) {
+ case NETDEV_PCPU_STAT_NONE:
+ return 0;
+ case NETDEV_PCPU_STAT_LSTATS:
+ v = dev->lstats = netdev_alloc_pcpu_stats(struct pcpu_lstats);
+ break;
+ case NETDEV_PCPU_STAT_TSTATS:
+ v = dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
+ break;
+ case NETDEV_PCPU_STAT_DSTATS:
+ v = dev->dstats = netdev_alloc_pcpu_stats(struct pcpu_dstats);
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ return v ? 0 : -ENOMEM;
+}
+
+static void netdev_do_free_pcpu_stats(struct net_device *dev)
+{
+ switch (dev->pcpu_stat_type) {
+ case NETDEV_PCPU_STAT_NONE:
+ return;
+ case NETDEV_PCPU_STAT_LSTATS:
+ free_percpu(dev->lstats);
+ break;
+ case NETDEV_PCPU_STAT_TSTATS:
+ free_percpu(dev->tstats);
+ break;
+ case NETDEV_PCPU_STAT_DSTATS:
+ free_percpu(dev->dstats);
+ break;
+ }
+}
+
/**
* register_netdevice() - register a network device
* @dev: device to register
@@ -10109,9 +10162,13 @@ int register_netdevice(struct net_device *dev)
goto err_uninit;
}
+ ret = netdev_do_alloc_pcpu_stats(dev);
+ if (ret)
+ goto err_uninit;
+
ret = dev_index_reserve(net, dev->ifindex);
if (ret < 0)
- goto err_uninit;
+ goto err_free_pcpu;
dev->ifindex = ret;
/* Transfer changeable features to wanted_features and enable
@@ -10217,6 +10274,8 @@ err_uninit_notify:
call_netdevice_notifiers(NETDEV_PRE_UNINIT, dev);
err_ifindex_release:
dev_index_release(net, dev->ifindex);
+err_free_pcpu:
+ netdev_do_free_pcpu_stats(dev);
err_uninit:
if (dev->netdev_ops->ndo_uninit)
dev->netdev_ops->ndo_uninit(dev);
@@ -10469,6 +10528,7 @@ void netdev_run_todo(void)
WARN_ON(rcu_access_pointer(dev->ip_ptr));
WARN_ON(rcu_access_pointer(dev->ip6_ptr));
+ netdev_do_free_pcpu_stats(dev);
if (dev->priv_destructor)
dev->priv_destructor(dev);
if (dev->needs_free_netdev)
diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c
index aff31cd944c2..b240d9aae4a6 100644
--- a/net/core/drop_monitor.c
+++ b/net/core/drop_monitor.c
@@ -183,7 +183,7 @@ out:
}
static const struct genl_multicast_group dropmon_mcgrps[] = {
- { .name = "events", },
+ { .name = "events", .cap_sys_admin = 1 },
};
static void send_dm_alert(struct work_struct *work)
@@ -1619,11 +1619,13 @@ static const struct genl_small_ops dropmon_ops[] = {
.cmd = NET_DM_CMD_START,
.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
.doit = net_dm_cmd_trace,
+ .flags = GENL_ADMIN_PERM,
},
{
.cmd = NET_DM_CMD_STOP,
.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
.doit = net_dm_cmd_trace,
+ .flags = GENL_ADMIN_PERM,
},
{
.cmd = NET_DM_CMD_CONFIG_GET,
diff --git a/net/core/filter.c b/net/core/filter.c
index 383f96b0a1c7..1737884be52f 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -81,6 +81,7 @@
#include <net/xdp.h>
#include <net/mptcp.h>
#include <net/netfilter/nf_conntrack_bpf.h>
+#include <net/netkit.h>
#include <linux/un.h>
#include "dev.h"
@@ -2468,6 +2469,16 @@ static const struct bpf_func_proto bpf_clone_redirect_proto = {
DEFINE_PER_CPU(struct bpf_redirect_info, bpf_redirect_info);
EXPORT_PER_CPU_SYMBOL_GPL(bpf_redirect_info);
+static struct net_device *skb_get_peer_dev(struct net_device *dev)
+{
+ const struct net_device_ops *ops = dev->netdev_ops;
+
+ if (likely(ops->ndo_get_peer_dev))
+ return INDIRECT_CALL_1(ops->ndo_get_peer_dev,
+ netkit_peer_dev, dev);
+ return NULL;
+}
+
int skb_do_redirect(struct sk_buff *skb)
{
struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
@@ -2481,17 +2492,15 @@ int skb_do_redirect(struct sk_buff *skb)
if (unlikely(!dev))
goto out_drop;
if (flags & BPF_F_PEER) {
- const struct net_device_ops *ops = dev->netdev_ops;
-
- if (unlikely(!ops->ndo_get_peer_dev ||
- !skb_at_tc_ingress(skb)))
+ if (unlikely(!skb_at_tc_ingress(skb)))
goto out_drop;
- dev = ops->ndo_get_peer_dev(dev);
+ dev = skb_get_peer_dev(dev);
if (unlikely(!dev ||
!(dev->flags & IFF_UP) ||
net_eq(net, dev_net(dev))))
goto out_drop;
skb->dev = dev;
+ dev_sw_netstats_rx_add(dev, skb->len);
return -EAGAIN;
}
return flags & BPF_F_NEIGH ?
@@ -2593,6 +2602,22 @@ BPF_CALL_2(bpf_msg_cork_bytes, struct sk_msg *, msg, u32, bytes)
return 0;
}
+static void sk_msg_reset_curr(struct sk_msg *msg)
+{
+ u32 i = msg->sg.start;
+ u32 len = 0;
+
+ do {
+ len += sk_msg_elem(msg, i)->length;
+ sk_msg_iter_var_next(i);
+ if (len >= msg->sg.size)
+ break;
+ } while (i != msg->sg.end);
+
+ msg->sg.curr = i;
+ msg->sg.copybreak = 0;
+}
+
static const struct bpf_func_proto bpf_msg_cork_bytes_proto = {
.func = bpf_msg_cork_bytes,
.gpl_only = false,
@@ -2712,6 +2737,7 @@ BPF_CALL_4(bpf_msg_pull_data, struct sk_msg *, msg, u32, start,
msg->sg.end - shift + NR_MSG_FRAG_IDS :
msg->sg.end - shift;
out:
+ sk_msg_reset_curr(msg);
msg->data = sg_virt(&msg->sg.data[first_sge]) + start - offset;
msg->data_end = msg->data + bytes;
return 0;
@@ -2848,6 +2874,7 @@ BPF_CALL_4(bpf_msg_push_data, struct sk_msg *, msg, u32, start,
msg->sg.data[new] = rsge;
}
+ sk_msg_reset_curr(msg);
sk_msg_compute_data_pointers(msg);
return 0;
}
@@ -3016,6 +3043,7 @@ BPF_CALL_4(bpf_msg_pop_data, struct sk_msg *, msg, u32, start,
sk_mem_uncharge(msg->sk, len - pop);
msg->sg.size -= (len - pop);
+ sk_msg_reset_curr(msg);
sk_msg_compute_data_pointers(msg);
return 0;
}
diff --git a/net/core/gso_test.c b/net/core/gso_test.c
index ceb684be4cbf..4c2e77bd12f4 100644
--- a/net/core/gso_test.c
+++ b/net/core/gso_test.c
@@ -180,18 +180,17 @@ static void gso_test_func(struct kunit *test)
}
if (tcase->frag_skbs) {
- unsigned int total_size = 0, total_true_size = 0, alloc_size = 0;
+ unsigned int total_size = 0, total_true_size = 0;
struct sk_buff *frag_skb, *prev = NULL;
- page = alloc_page(GFP_KERNEL);
- KUNIT_ASSERT_NOT_NULL(test, page);
- page_ref_add(page, tcase->nr_frag_skbs - 1);
-
for (i = 0; i < tcase->nr_frag_skbs; i++) {
unsigned int frag_size;
+ page = alloc_page(GFP_KERNEL);
+ KUNIT_ASSERT_NOT_NULL(test, page);
+
frag_size = tcase->frag_skbs[i];
- frag_skb = build_skb(page_address(page) + alloc_size,
+ frag_skb = build_skb(page_address(page),
frag_size + shinfo_size);
KUNIT_ASSERT_NOT_NULL(test, frag_skb);
__skb_put(frag_skb, frag_size);
@@ -204,11 +203,8 @@ static void gso_test_func(struct kunit *test)
total_size += frag_size;
total_true_size += frag_skb->truesize;
- alloc_size += frag_size + shinfo_size;
}
- KUNIT_ASSERT_LE(test, alloc_size, PAGE_SIZE);
-
skb->len += total_size;
skb->data_len += total_size;
skb->truesize += total_true_size;
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index df81c1f0a570..552719c3bbc3 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -253,9 +253,11 @@ static int neigh_forced_gc(struct neigh_table *tbl)
{
int max_clean = atomic_read(&tbl->gc_entries) -
READ_ONCE(tbl->gc_thresh2);
+ u64 tmax = ktime_get_ns() + NSEC_PER_MSEC;
unsigned long tref = jiffies - 5 * HZ;
struct neighbour *n, *tmp;
int shrunk = 0;
+ int loop = 0;
NEIGH_CACHE_STAT_INC(tbl, forced_gc_runs);
@@ -278,11 +280,16 @@ static int neigh_forced_gc(struct neigh_table *tbl)
shrunk++;
if (shrunk >= max_clean)
break;
+ if (++loop == 16) {
+ if (ktime_get_ns() > tmax)
+ goto unlock;
+ loop = 0;
+ }
}
}
WRITE_ONCE(tbl->last_flush, jiffies);
-
+unlock:
write_unlock_bh(&tbl->lock);
return shrunk;
diff --git a/net/core/scm.c b/net/core/scm.c
index 880027ecf516..db3f7cd519c2 100644
--- a/net/core/scm.c
+++ b/net/core/scm.c
@@ -26,6 +26,7 @@
#include <linux/nsproxy.h>
#include <linux/slab.h>
#include <linux/errqueue.h>
+#include <linux/io_uring.h>
#include <linux/uaccess.h>
@@ -103,6 +104,11 @@ static int scm_fp_copy(struct cmsghdr *cmsg, struct scm_fp_list **fplp)
if (fd < 0 || !(file = fget_raw(fd)))
return -EBADF;
+ /* don't allow io_uring files */
+ if (io_uring_get_socket(file)) {
+ fput(file);
+ return -EINVAL;
+ }
*fpp++ = file;
fpl->count++;
}
@@ -319,7 +325,7 @@ void scm_detach_fds(struct msghdr *msg, struct scm_cookie *scm)
}
for (i = 0; i < fdmax; i++) {
- err = receive_fd_user(scm->fp->fp[i], cmsg_data + i, o_flags);
+ err = scm_recv_one_fd(scm->fp->fp[i], cmsg_data + i, o_flags);
if (err < 0)
break;
}
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index b157efea5dea..94cc40a6f797 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -4522,8 +4522,9 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb,
/* GSO partial only requires that we trim off any excess that
* doesn't fit into an MSS sized block, so take care of that
* now.
+ * Cap len to not accidentally hit GSO_BY_FRAGS.
*/
- partial_segs = len / mss;
+ partial_segs = min(len, GSO_BY_FRAGS - 1) / mss;
if (partial_segs > 1)
mss *= partial_segs;
else
@@ -4824,7 +4825,9 @@ static __always_inline unsigned int skb_ext_total_length(void)
static void skb_extensions_init(void)
{
BUILD_BUG_ON(SKB_EXT_NUM >= 8);
+#if !IS_ENABLED(CONFIG_KCOV_INSTRUMENT_ALL)
BUILD_BUG_ON(skb_ext_total_length() > 255);
+#endif
skbuff_ext_cache = kmem_cache_create("skbuff_ext_cache",
SKB_EXT_ALIGN_VALUE * skb_ext_total_length(),
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 6c31eefbd777..93ecfceac1bc 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -826,6 +826,8 @@ static void sk_psock_destroy(struct work_struct *work)
if (psock->sk_redir)
sock_put(psock->sk_redir);
+ if (psock->sk_pair)
+ sock_put(psock->sk_pair);
sock_put(psock->sk);
kfree(psock);
}
diff --git a/net/core/sock.c b/net/core/sock.c
index fef349dd72fa..d02534c77413 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1711,9 +1711,16 @@ int sk_getsockopt(struct sock *sk, int level, int optname,
break;
case SO_TIMESTAMPING_OLD:
+ case SO_TIMESTAMPING_NEW:
lv = sizeof(v.timestamping);
- v.timestamping.flags = READ_ONCE(sk->sk_tsflags);
- v.timestamping.bind_phc = READ_ONCE(sk->sk_bind_phc);
+ /* For the later-added case SO_TIMESTAMPING_NEW: Be strict about only
+ * returning the flags when they were set through the same option.
+ * Don't change the beviour for the old case SO_TIMESTAMPING_OLD.
+ */
+ if (optname == SO_TIMESTAMPING_OLD || sock_flag(sk, SOCK_TSTAMP_NEW)) {
+ v.timestamping.flags = READ_ONCE(sk->sk_tsflags);
+ v.timestamping.bind_phc = READ_ONCE(sk->sk_bind_phc);
+ }
break;
case SO_RCVTIMEO_OLD:
@@ -2806,6 +2813,7 @@ int __sock_cmsg_send(struct sock *sk, struct cmsghdr *cmsg,
sockc->mark = *(u32 *)CMSG_DATA(cmsg);
break;
case SO_TIMESTAMPING_OLD:
+ case SO_TIMESTAMPING_NEW:
if (cmsg->cmsg_len != CMSG_LEN(sizeof(u32)))
return -EINVAL;
diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index 4292c2ed1828..27d733c0f65e 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -536,6 +536,8 @@ static bool sock_map_sk_state_allowed(const struct sock *sk)
{
if (sk_is_tcp(sk))
return (1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_LISTEN);
+ if (sk_is_stream_unix(sk))
+ return (1 << sk->sk_state) & TCPF_ESTABLISHED;
return true;
}
diff --git a/net/core/stream.c b/net/core/stream.c
index 96fbcb9bbb30..b16dfa568a2d 100644
--- a/net/core/stream.c
+++ b/net/core/stream.c
@@ -79,7 +79,7 @@ int sk_stream_wait_connect(struct sock *sk, long *timeo_p)
remove_wait_queue(sk_sleep(sk), &wait);
sk->sk_write_pending--;
} while (!done);
- return 0;
+ return done < 0 ? done : 0;
}
EXPORT_SYMBOL(sk_stream_wait_connect);
Powered by cgit, Gruvboxed by Blaster4385.