summaryrefslogtreecommitdiff
path: root/net/core
diff options
context:
space:
mode:
Diffstat (limited to 'net/core')
-rw-r--r--net/core/Makefile1
-rw-r--r--net/core/dev.c32
-rw-r--r--net/core/flow_dissector.c6
-rw-r--r--net/core/neighbour.c2
-rw-r--r--net/core/rtnetlink.c17
-rw-r--r--net/core/scm.c23
-rw-r--r--net/core/selftests.c400
-rw-r--r--net/core/skbuff.c15
-rw-r--r--net/core/skmsg.c12
-rw-r--r--net/core/sock.c14
-rw-r--r--net/core/xdp.c3
11 files changed, 479 insertions, 46 deletions
diff --git a/net/core/Makefile b/net/core/Makefile
index 0c2233c826fd..1a6168d8f23b 100644
--- a/net/core/Makefile
+++ b/net/core/Makefile
@@ -33,6 +33,7 @@ obj-$(CONFIG_NET_DEVLINK) += devlink.o
obj-$(CONFIG_GRO_CELLS) += gro_cells.o
obj-$(CONFIG_FAILOVER) += failover.o
ifeq ($(CONFIG_INET),y)
+obj-$(CONFIG_NET_SELFTESTS) += selftests.o
obj-$(CONFIG_NET_SOCK_MSG) += skmsg.o
obj-$(CONFIG_BPF_SYSCALL) += sock_map.o
endif
diff --git a/net/core/dev.c b/net/core/dev.c
index 6a1ef7a15bed..eed028aec6a4 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5976,7 +5976,8 @@ static void skb_gro_reset_offset(struct sk_buff *skb)
NAPI_GRO_CB(skb)->frag0_len = 0;
if (!skb_headlen(skb) && pinfo->nr_frags &&
- !PageHighMem(skb_frag_page(frag0))) {
+ !PageHighMem(skb_frag_page(frag0)) &&
+ (!NET_IP_ALIGN || !(skb_frag_off(frag0) & 3))) {
NAPI_GRO_CB(skb)->frag0 = skb_frag_address(frag0);
NAPI_GRO_CB(skb)->frag0_len = min_t(unsigned int,
skb_frag_size(frag0),
@@ -7045,7 +7046,7 @@ static int napi_thread_wait(struct napi_struct *napi)
set_current_state(TASK_INTERRUPTIBLE);
- while (!kthread_should_stop() && !napi_disable_pending(napi)) {
+ while (!kthread_should_stop()) {
/* Testing SCHED_THREADED bit here to make sure the current
* kthread owns this napi and could poll on this napi.
* Testing SCHED bit is not enough because SCHED bit might be
@@ -7063,6 +7064,7 @@ static int napi_thread_wait(struct napi_struct *napi)
set_current_state(TASK_INTERRUPTIBLE);
}
__set_current_state(TASK_RUNNING);
+
return -1;
}
@@ -11066,11 +11068,13 @@ void unregister_netdev(struct net_device *dev)
EXPORT_SYMBOL(unregister_netdev);
/**
- * dev_change_net_namespace - move device to different nethost namespace
+ * __dev_change_net_namespace - move device to different nethost namespace
* @dev: device
* @net: network namespace
* @pat: If not NULL name pattern to try if the current device name
* is already taken in the destination network namespace.
+ * @new_ifindex: If not zero, specifies device index in the target
+ * namespace.
*
* This function shuts down a device interface and moves it
* to a new network namespace. On success 0 is returned, on
@@ -11079,10 +11083,11 @@ EXPORT_SYMBOL(unregister_netdev);
* Callers must hold the rtnl semaphore.
*/
-int dev_change_net_namespace(struct net_device *dev, struct net *net, const char *pat)
+int __dev_change_net_namespace(struct net_device *dev, struct net *net,
+ const char *pat, int new_ifindex)
{
struct net *net_old = dev_net(dev);
- int err, new_nsid, new_ifindex;
+ int err, new_nsid;
ASSERT_RTNL();
@@ -11113,6 +11118,11 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char
goto out;
}
+ /* Check that new_ifindex isn't used yet. */
+ err = -EBUSY;
+ if (new_ifindex && __dev_get_by_index(net, new_ifindex))
+ goto out;
+
/*
* And now a mini version of register_netdevice unregister_netdevice.
*/
@@ -11140,10 +11150,12 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char
new_nsid = peernet2id_alloc(dev_net(dev), net, GFP_KERNEL);
/* If there is an ifindex conflict assign a new one */
- if (__dev_get_by_index(net, dev->ifindex))
- new_ifindex = dev_new_index(net);
- else
- new_ifindex = dev->ifindex;
+ if (!new_ifindex) {
+ if (__dev_get_by_index(net, dev->ifindex))
+ new_ifindex = dev_new_index(net);
+ else
+ new_ifindex = dev->ifindex;
+ }
rtmsg_ifinfo_newnet(RTM_DELLINK, dev, ~0U, GFP_KERNEL, &new_nsid,
new_ifindex);
@@ -11196,7 +11208,7 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char
out:
return err;
}
-EXPORT_SYMBOL_GPL(dev_change_net_namespace);
+EXPORT_SYMBOL_GPL(__dev_change_net_namespace);
static int dev_cpu_dead(unsigned int oldcpu)
{
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 5985029e43d4..3ed7c98a98e1 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -832,8 +832,10 @@ static void __skb_flow_bpf_to_target(const struct bpf_flow_keys *flow_keys,
key_addrs = skb_flow_dissector_target(flow_dissector,
FLOW_DISSECTOR_KEY_IPV6_ADDRS,
target_container);
- memcpy(&key_addrs->v6addrs, &flow_keys->ipv6_src,
- sizeof(key_addrs->v6addrs));
+ memcpy(&key_addrs->v6addrs.src, &flow_keys->ipv6_src,
+ sizeof(key_addrs->v6addrs.src));
+ memcpy(&key_addrs->v6addrs.dst, &flow_keys->ipv6_dst,
+ sizeof(key_addrs->v6addrs.dst));
key_control->addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS;
}
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index e2982b3970b8..8379719d1dce 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -1379,7 +1379,7 @@ static int __neigh_update(struct neighbour *neigh, const u8 *lladdr,
* we can reinject the packet there.
*/
n2 = NULL;
- if (dst) {
+ if (dst && dst->obsolete != DST_OBSOLETE_DEAD) {
n2 = dst_neigh_lookup_skb(dst, skb);
if (n2)
n1 = n2;
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 1bdcb33fb561..714d5fa38546 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1877,6 +1877,7 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = {
.len = ALTIFNAMSIZ - 1 },
[IFLA_PERM_ADDRESS] = { .type = NLA_REJECT },
[IFLA_PROTO_DOWN_REASON] = { .type = NLA_NESTED },
+ [IFLA_NEW_IFINDEX] = NLA_POLICY_MIN(NLA_S32, 1),
};
static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = {
@@ -2603,14 +2604,22 @@ static int do_setlink(const struct sk_buff *skb,
return err;
if (tb[IFLA_NET_NS_PID] || tb[IFLA_NET_NS_FD] || tb[IFLA_TARGET_NETNSID]) {
- struct net *net = rtnl_link_get_net_capable(skb, dev_net(dev),
- tb, CAP_NET_ADMIN);
+ struct net *net;
+ int new_ifindex;
+
+ net = rtnl_link_get_net_capable(skb, dev_net(dev),
+ tb, CAP_NET_ADMIN);
if (IS_ERR(net)) {
err = PTR_ERR(net);
goto errout;
}
- err = dev_change_net_namespace(dev, net, ifname);
+ if (tb[IFLA_NEW_IFINDEX])
+ new_ifindex = nla_get_s32(tb[IFLA_NEW_IFINDEX]);
+ else
+ new_ifindex = 0;
+
+ err = __dev_change_net_namespace(dev, net, ifname, new_ifindex);
put_net(net);
if (err)
goto errout;
@@ -2863,7 +2872,7 @@ static int do_setlink(const struct sk_buff *skb,
BUG_ON(!(af_ops = rtnl_af_lookup(nla_type(af))));
- err = af_ops->set_link_af(dev, af);
+ err = af_ops->set_link_af(dev, af, extack);
if (err < 0) {
rcu_read_unlock();
goto errout;
diff --git a/net/core/scm.c b/net/core/scm.c
index 8156d4fb8a39..ae3085d9aae8 100644
--- a/net/core/scm.c
+++ b/net/core/scm.c
@@ -228,14 +228,16 @@ int put_cmsg(struct msghdr * msg, int level, int type, int len, void *data)
if (msg->msg_control_is_user) {
struct cmsghdr __user *cm = msg->msg_control_user;
- struct cmsghdr cmhdr;
-
- cmhdr.cmsg_level = level;
- cmhdr.cmsg_type = type;
- cmhdr.cmsg_len = cmlen;
- if (copy_to_user(cm, &cmhdr, sizeof cmhdr) ||
- copy_to_user(CMSG_USER_DATA(cm), data, cmlen - sizeof(*cm)))
- return -EFAULT;
+
+ if (!user_write_access_begin(cm, cmlen))
+ goto efault;
+
+ unsafe_put_user(cmlen, &cm->cmsg_len, efault_end);
+ unsafe_put_user(level, &cm->cmsg_level, efault_end);
+ unsafe_put_user(type, &cm->cmsg_type, efault_end);
+ unsafe_copy_to_user(CMSG_USER_DATA(cm), data,
+ cmlen - sizeof(*cm), efault_end);
+ user_write_access_end();
} else {
struct cmsghdr *cm = msg->msg_control;
@@ -249,6 +251,11 @@ int put_cmsg(struct msghdr * msg, int level, int type, int len, void *data)
msg->msg_control += cmlen;
msg->msg_controllen -= cmlen;
return 0;
+
+efault_end:
+ user_write_access_end();
+efault:
+ return -EFAULT;
}
EXPORT_SYMBOL(put_cmsg);
diff --git a/net/core/selftests.c b/net/core/selftests.c
new file mode 100644
index 000000000000..ba7b0171974c
--- /dev/null
+++ b/net/core/selftests.c
@@ -0,0 +1,400 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2019 Synopsys, Inc. and/or its affiliates.
+ * stmmac Selftests Support
+ *
+ * Author: Jose Abreu <joabreu@synopsys.com>
+ *
+ * Ported from stmmac by:
+ * Copyright (C) 2021 Oleksij Rempel <o.rempel@pengutronix.de>
+ */
+
+#include <linux/phy.h>
+#include <net/selftests.h>
+#include <net/tcp.h>
+#include <net/udp.h>
+
+struct net_packet_attrs {
+ unsigned char *src;
+ unsigned char *dst;
+ u32 ip_src;
+ u32 ip_dst;
+ bool tcp;
+ u16 sport;
+ u16 dport;
+ int timeout;
+ int size;
+ int max_size;
+ u8 id;
+ u16 queue_mapping;
+};
+
+struct net_test_priv {
+ struct net_packet_attrs *packet;
+ struct packet_type pt;
+ struct completion comp;
+ int double_vlan;
+ int vlan_id;
+ int ok;
+};
+
+struct netsfhdr {
+ __be32 version;
+ __be64 magic;
+ u8 id;
+} __packed;
+
+static u8 net_test_next_id;
+
+#define NET_TEST_PKT_SIZE (sizeof(struct ethhdr) + sizeof(struct iphdr) + \
+ sizeof(struct netsfhdr))
+#define NET_TEST_PKT_MAGIC 0xdeadcafecafedeadULL
+#define NET_LB_TIMEOUT msecs_to_jiffies(200)
+
+static struct sk_buff *net_test_get_skb(struct net_device *ndev,
+ struct net_packet_attrs *attr)
+{
+ struct sk_buff *skb = NULL;
+ struct udphdr *uhdr = NULL;
+ struct tcphdr *thdr = NULL;
+ struct netsfhdr *shdr;
+ struct ethhdr *ehdr;
+ struct iphdr *ihdr;
+ int iplen, size;
+
+ size = attr->size + NET_TEST_PKT_SIZE;
+
+ if (attr->tcp)
+ size += sizeof(struct tcphdr);
+ else
+ size += sizeof(struct udphdr);
+
+ if (attr->max_size && attr->max_size > size)
+ size = attr->max_size;
+
+ skb = netdev_alloc_skb(ndev, size);
+ if (!skb)
+ return NULL;
+
+ prefetchw(skb->data);
+
+ ehdr = skb_push(skb, ETH_HLEN);
+ skb_reset_mac_header(skb);
+
+ skb_set_network_header(skb, skb->len);
+ ihdr = skb_put(skb, sizeof(*ihdr));
+
+ skb_set_transport_header(skb, skb->len);
+ if (attr->tcp)
+ thdr = skb_put(skb, sizeof(*thdr));
+ else
+ uhdr = skb_put(skb, sizeof(*uhdr));
+
+ eth_zero_addr(ehdr->h_dest);
+
+ if (attr->src)
+ ether_addr_copy(ehdr->h_source, attr->src);
+ if (attr->dst)
+ ether_addr_copy(ehdr->h_dest, attr->dst);
+
+ ehdr->h_proto = htons(ETH_P_IP);
+
+ if (attr->tcp) {
+ 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);
+ uhdr->len = htons(sizeof(*shdr) + sizeof(*uhdr) + attr->size);
+ if (attr->max_size)
+ uhdr->len = htons(attr->max_size -
+ (sizeof(*ihdr) + sizeof(*ehdr)));
+ uhdr->check = 0;
+ }
+
+ ihdr->ihl = 5;
+ ihdr->ttl = 32;
+ ihdr->version = 4;
+ if (attr->tcp)
+ ihdr->protocol = IPPROTO_TCP;
+ else
+ ihdr->protocol = IPPROTO_UDP;
+ iplen = sizeof(*ihdr) + sizeof(*shdr) + attr->size;
+ if (attr->tcp)
+ iplen += sizeof(*thdr);
+ else
+ iplen += sizeof(*uhdr);
+
+ if (attr->max_size)
+ iplen = attr->max_size - sizeof(*ehdr);
+
+ ihdr->tot_len = htons(iplen);
+ ihdr->frag_off = 0;
+ ihdr->saddr = htonl(attr->ip_src);
+ ihdr->daddr = htonl(attr->ip_dst);
+ ihdr->tos = 0;
+ ihdr->id = 0;
+ ip_send_check(ihdr);
+
+ shdr = skb_put(skb, sizeof(*shdr));
+ shdr->version = 0;
+ shdr->magic = cpu_to_be64(NET_TEST_PKT_MAGIC);
+ 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);
+
+ skb->csum = 0;
+ skb->ip_summed = CHECKSUM_PARTIAL;
+ if (attr->tcp) {
+ thdr->check = ~tcp_v4_check(skb->len, ihdr->saddr,
+ ihdr->daddr, 0);
+ skb->csum_start = skb_transport_header(skb) - skb->head;
+ skb->csum_offset = offsetof(struct tcphdr, check);
+ } else {
+ udp4_hwcsum(skb, ihdr->saddr, ihdr->daddr);
+ }
+
+ skb->protocol = htons(ETH_P_IP);
+ skb->pkt_type = PACKET_HOST;
+ skb->dev = ndev;
+
+ return skb;
+}
+
+static int net_test_loopback_validate(struct sk_buff *skb,
+ struct net_device *ndev,
+ struct packet_type *pt,
+ struct net_device *orig_ndev)
+{
+ struct net_test_priv *tpriv = pt->af_packet_priv;
+ unsigned char *src = tpriv->packet->src;
+ unsigned char *dst = tpriv->packet->dst;
+ struct netsfhdr *shdr;
+ struct ethhdr *ehdr;
+ struct udphdr *uhdr;
+ struct tcphdr *thdr;
+ struct iphdr *ihdr;
+
+ skb = skb_unshare(skb, GFP_ATOMIC);
+ if (!skb)
+ goto out;
+
+ if (skb_linearize(skb))
+ goto out;
+ if (skb_headlen(skb) < (NET_TEST_PKT_SIZE - ETH_HLEN))
+ goto out;
+
+ ehdr = (struct ethhdr *)skb_mac_header(skb);
+ if (dst) {
+ if (!ether_addr_equal_unaligned(ehdr->h_dest, dst))
+ goto out;
+ }
+
+ if (src) {
+ if (!ether_addr_equal_unaligned(ehdr->h_source, src))
+ goto out;
+ }
+
+ ihdr = ip_hdr(skb);
+ if (tpriv->double_vlan)
+ ihdr = (struct iphdr *)(skb_network_header(skb) + 4);
+
+ if (tpriv->packet->tcp) {
+ if (ihdr->protocol != IPPROTO_TCP)
+ goto out;
+
+ thdr = (struct tcphdr *)((u8 *)ihdr + 4 * ihdr->ihl);
+ if (thdr->dest != htons(tpriv->packet->dport))
+ goto out;
+
+ shdr = (struct netsfhdr *)((u8 *)thdr + sizeof(*thdr));
+ } else {
+ if (ihdr->protocol != IPPROTO_UDP)
+ goto out;
+
+ uhdr = (struct udphdr *)((u8 *)ihdr + 4 * ihdr->ihl);
+ if (uhdr->dest != htons(tpriv->packet->dport))
+ goto out;
+
+ shdr = (struct netsfhdr *)((u8 *)uhdr + sizeof(*uhdr));
+ }
+
+ if (shdr->magic != cpu_to_be64(NET_TEST_PKT_MAGIC))
+ goto out;
+ if (tpriv->packet->id != shdr->id)
+ goto out;
+
+ tpriv->ok = true;
+ complete(&tpriv->comp);
+out:
+ kfree_skb(skb);
+ return 0;
+}
+
+static int __net_test_loopback(struct net_device *ndev,
+ struct net_packet_attrs *attr)
+{
+ struct net_test_priv *tpriv;
+ struct sk_buff *skb = NULL;
+ int ret = 0;
+
+ tpriv = kzalloc(sizeof(*tpriv), GFP_KERNEL);
+ if (!tpriv)
+ return -ENOMEM;
+
+ tpriv->ok = false;
+ init_completion(&tpriv->comp);
+
+ tpriv->pt.type = htons(ETH_P_IP);
+ tpriv->pt.func = net_test_loopback_validate;
+ tpriv->pt.dev = ndev;
+ tpriv->pt.af_packet_priv = tpriv;
+ tpriv->packet = attr;
+ dev_add_pack(&tpriv->pt);
+
+ skb = net_test_get_skb(ndev, attr);
+ if (!skb) {
+ ret = -ENOMEM;
+ goto cleanup;
+ }
+
+ ret = dev_direct_xmit(skb, attr->queue_mapping);
+ if (ret < 0) {
+ goto cleanup;
+ } else if (ret > 0) {
+ ret = -ENETUNREACH;
+ goto cleanup;
+ }
+
+ if (!attr->timeout)
+ attr->timeout = NET_LB_TIMEOUT;
+
+ wait_for_completion_timeout(&tpriv->comp, attr->timeout);
+ ret = tpriv->ok ? 0 : -ETIMEDOUT;
+
+cleanup:
+ dev_remove_pack(&tpriv->pt);
+ kfree(tpriv);
+ return ret;
+}
+
+static int net_test_netif_carrier(struct net_device *ndev)
+{
+ return netif_carrier_ok(ndev) ? 0 : -ENOLINK;
+}
+
+static int net_test_phy_phydev(struct net_device *ndev)
+{
+ return ndev->phydev ? 0 : -EOPNOTSUPP;
+}
+
+static int net_test_phy_loopback_enable(struct net_device *ndev)
+{
+ if (!ndev->phydev)
+ return -EOPNOTSUPP;
+
+ return phy_loopback(ndev->phydev, true);
+}
+
+static int net_test_phy_loopback_disable(struct net_device *ndev)
+{
+ if (!ndev->phydev)
+ return -EOPNOTSUPP;
+
+ return phy_loopback(ndev->phydev, false);
+}
+
+static int net_test_phy_loopback_udp(struct net_device *ndev)
+{
+ struct net_packet_attrs attr = { };
+
+ attr.dst = ndev->dev_addr;
+ return __net_test_loopback(ndev, &attr);
+}
+
+static int net_test_phy_loopback_tcp(struct net_device *ndev)
+{
+ struct net_packet_attrs attr = { };
+
+ attr.dst = ndev->dev_addr;
+ attr.tcp = true;
+ return __net_test_loopback(ndev, &attr);
+}
+
+static const struct net_test {
+ char name[ETH_GSTRING_LEN];
+ int (*fn)(struct net_device *ndev);
+} net_selftests[] = {
+ {
+ .name = "Carrier ",
+ .fn = net_test_netif_carrier,
+ }, {
+ .name = "PHY dev is present ",
+ .fn = net_test_phy_phydev,
+ }, {
+ /* This test should be done before all PHY loopback test */
+ .name = "PHY internal loopback, enable ",
+ .fn = net_test_phy_loopback_enable,
+ }, {
+ .name = "PHY internal loopback, UDP ",
+ .fn = net_test_phy_loopback_udp,
+ }, {
+ .name = "PHY internal loopback, TCP ",
+ .fn = net_test_phy_loopback_tcp,
+ }, {
+ /* This test should be done after all PHY loopback test */
+ .name = "PHY internal loopback, disable",
+ .fn = net_test_phy_loopback_disable,
+ },
+};
+
+void net_selftest(struct net_device *ndev, struct ethtool_test *etest, u64 *buf)
+{
+ int count = net_selftest_get_count();
+ int i;
+
+ memset(buf, 0, sizeof(*buf) * count);
+ net_test_next_id = 0;
+
+ if (etest->flags != ETH_TEST_FL_OFFLINE) {
+ netdev_err(ndev, "Only offline tests are supported\n");
+ etest->flags |= ETH_TEST_FL_FAILED;
+ return;
+ }
+
+
+ for (i = 0; i < count; i++) {
+ buf[i] = net_selftests[i].fn(ndev);
+ if (buf[i] && (buf[i] != -EOPNOTSUPP))
+ etest->flags |= ETH_TEST_FL_FAILED;
+ }
+}
+EXPORT_SYMBOL_GPL(net_selftest);
+
+int net_selftest_get_count(void)
+{
+ return ARRAY_SIZE(net_selftests);
+}
+EXPORT_SYMBOL_GPL(net_selftest_get_count);
+
+void net_selftest_get_strings(u8 *data)
+{
+ u8 *p = data;
+ int i;
+
+ for (i = 0; i < net_selftest_get_count(); i++) {
+ snprintf(p, ETH_GSTRING_LEN, "%2d. %s", i + 1,
+ net_selftests[i].name);
+ p += ETH_GSTRING_LEN;
+ }
+}
+EXPORT_SYMBOL_GPL(net_selftest_get_strings);
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Oleksij Rempel <o.rempel@pengutronix.de>");
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 3ad9e8425ab2..14010c0eec48 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3773,13 +3773,13 @@ struct sk_buff *skb_segment_list(struct sk_buff *skb,
unsigned int tnl_hlen = skb_tnl_header_len(skb);
unsigned int delta_truesize = 0;
unsigned int delta_len = 0;
+ struct sk_buff *tail = NULL;
struct sk_buff *nskb, *tmp;
int err;
skb_push(skb, -skb_network_offset(skb) + offset);
skb_shinfo(skb)->frag_list = NULL;
- skb->next = list_skb;
do {
nskb = list_skb;
@@ -3797,8 +3797,17 @@ struct sk_buff *skb_segment_list(struct sk_buff *skb,
}
}
- if (unlikely(err))
+ if (!tail)
+ skb->next = nskb;
+ else
+ tail->next = nskb;
+
+ if (unlikely(err)) {
+ nskb->next = list_skb;
goto err_linearize;
+ }
+
+ tail = nskb;
delta_len += nskb->len;
delta_truesize += nskb->truesize;
@@ -3825,7 +3834,7 @@ struct sk_buff *skb_segment_list(struct sk_buff *skb,
skb_gso_reset(skb);
- skb->prev = nskb;
+ skb->prev = tail;
if (skb_needs_linearize(skb, features) &&
__skb_linearize(skb))
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 92a83c02562a..43ce17a6a585 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -586,6 +586,7 @@ static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb
if (unlikely(!msg))
return -EAGAIN;
sk_msg_init(msg);
+ skb_set_owner_r(skb, sk);
return sk_psock_skb_ingress_enqueue(skb, psock, sk, msg);
}
@@ -884,7 +885,6 @@ static void sk_psock_tls_verdict_apply(struct sk_buff *skb, struct sock *sk, int
{
switch (verdict) {
case __SK_REDIRECT:
- skb_set_owner_r(skb, sk);
sk_psock_skb_redirect(skb);
break;
case __SK_PASS:
@@ -902,10 +902,6 @@ int sk_psock_tls_strp_read(struct sk_psock *psock, struct sk_buff *skb)
rcu_read_lock();
prog = READ_ONCE(psock->progs.stream_verdict);
if (likely(prog)) {
- /* We skip full set_owner_r here because if we do a SK_PASS
- * or SK_DROP we can skip skb memory accounting and use the
- * TLS context.
- */
skb->sk = psock->sk;
skb_dst_drop(skb);
skb_bpf_redirect_clear(skb);
@@ -995,13 +991,14 @@ static void sk_psock_strp_read(struct strparser *strp, struct sk_buff *skb)
kfree_skb(skb);
goto out;
}
- skb_set_owner_r(skb, sk);
prog = READ_ONCE(psock->progs.stream_verdict);
if (likely(prog)) {
+ skb->sk = sk;
skb_dst_drop(skb);
skb_bpf_redirect_clear(skb);
ret = bpf_prog_run_pin_on_cpu(prog, skb);
ret = sk_psock_map_verd(ret, skb_bpf_redirect_fetch(skb));
+ skb->sk = NULL;
}
sk_psock_verdict_apply(psock, skb, ret);
out:
@@ -1115,15 +1112,16 @@ static int sk_psock_verdict_recv(read_descriptor_t *desc, struct sk_buff *skb,
kfree_skb(skb);
goto out;
}
- skb_set_owner_r(skb, sk);
prog = READ_ONCE(psock->progs.stream_verdict);
if (!prog)
prog = READ_ONCE(psock->progs.skb_verdict);
if (likely(prog)) {
+ skb->sk = sk;
skb_dst_drop(skb);
skb_bpf_redirect_clear(skb);
ret = bpf_prog_run_pin_on_cpu(prog, skb);
ret = sk_psock_map_verd(ret, skb_bpf_redirect_fetch(skb));
+ skb->sk = NULL;
}
sk_psock_verdict_apply(psock, skb, ret);
out:
diff --git a/net/core/sock.c b/net/core/sock.c
index cc31b601ae10..c761c4a0b66b 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2132,16 +2132,10 @@ void skb_orphan_partial(struct sk_buff *skb)
if (skb_is_tcp_pure_ack(skb))
return;
- if (can_skb_orphan_partial(skb)) {
- struct sock *sk = skb->sk;
-
- if (refcount_inc_not_zero(&sk->sk_refcnt)) {
- WARN_ON(refcount_sub_and_test(skb->truesize, &sk->sk_wmem_alloc));
- skb->destructor = sock_efree;
- }
- } else {
+ if (can_skb_orphan_partial(skb))
+ skb_set_owner_sk_safe(skb, skb->sk);
+ else
skb_orphan(skb);
- }
}
EXPORT_SYMBOL(skb_orphan_partial);
@@ -3537,7 +3531,7 @@ int proto_register(struct proto *prot, int alloc_slab)
return ret;
out_free_timewait_sock_slab:
- if (alloc_slab && prot->twsk_prot)
+ if (alloc_slab)
tw_prot_cleanup(prot->twsk_prot);
out_free_request_sock_slab:
if (alloc_slab) {
diff --git a/net/core/xdp.c b/net/core/xdp.c
index 05354976c1fc..858276e72c68 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -350,7 +350,8 @@ static void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct,
/* mem->id is valid, checked in xdp_rxq_info_reg_mem_model() */
xa = rhashtable_lookup(mem_id_ht, &mem->id, mem_id_rht_params);
page = virt_to_head_page(data);
- napi_direct &= !xdp_return_frame_no_direct();
+ if (napi_direct && xdp_return_frame_no_direct())
+ napi_direct = false;
page_pool_put_full_page(xa->page_pool, page, napi_direct);
rcu_read_unlock();
break;
generated by cgit v1.2.3 (git 2.39.0) at 2024-07-23 06:48:29 +0300