aboutsummaryrefslogtreecommitdiffstats
path: root/net/core
diff options
context:
space:
mode:
Diffstat (limited to 'net/core')
-rw-r--r--net/core/dev.c14
-rw-r--r--net/core/ethtool.c158
-rw-r--r--net/core/filter.c87
-rw-r--r--net/core/neighbour.c13
-rw-r--r--net/core/pktgen.c2
-rw-r--r--net/core/rtnetlink.c57
-rw-r--r--net/core/skbuff.c3
-rw-r--r--net/core/sock.c2
-rw-r--r--net/core/xdp.c53
9 files changed, 193 insertions, 196 deletions
diff --git a/net/core/dev.c b/net/core/dev.c
index 325fc5088370..0b2d777e5b9e 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -93,7 +93,6 @@
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/ethtool.h>
-#include <linux/notifier.h>
#include <linux/skbuff.h>
#include <linux/bpf.h>
#include <linux/bpf_trace.h>
@@ -1970,6 +1969,9 @@ void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev)
rcu_read_lock();
again:
list_for_each_entry_rcu(ptype, ptype_list, list) {
+ if (ptype->ignore_outgoing)
+ continue;
+
/* Never send packets back to the socket
* they originated from - MvS (miquels@drinkel.ow.org)
*/
@@ -3229,7 +3231,7 @@ struct sk_buff *dev_hard_start_xmit(struct sk_buff *first, struct net_device *de
while (skb) {
struct sk_buff *next = skb->next;
- skb->next = NULL;
+ skb_mark_not_on_list(skb);
rc = xmit_one(skb, dev, txq, next != NULL);
if (unlikely(!dev_xmit_complete(rc))) {
skb->next = next;
@@ -3329,7 +3331,7 @@ struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *d
for (; skb != NULL; skb = next) {
next = skb->next;
- skb->next = NULL;
+ skb_mark_not_on_list(skb);
/* in case skb wont be segmented, point to itself */
skb->prev = skb;
@@ -5293,8 +5295,7 @@ static void __napi_gro_flush_chain(struct napi_struct *napi, u32 index,
list_for_each_entry_safe_reverse(skb, p, head, list) {
if (flush_old && NAPI_GRO_CB(skb)->age == jiffies)
return;
- list_del(&skb->list);
- skb->next = NULL;
+ skb_list_del_init(skb);
napi_gro_complete(skb);
napi->gro_hash[index].count--;
}
@@ -5479,8 +5480,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
ret = NAPI_GRO_CB(skb)->free ? GRO_MERGED_FREE : GRO_MERGED;
if (pp) {
- list_del(&pp->list);
- pp->next = NULL;
+ skb_list_del_init(pp);
napi_gro_complete(pp);
napi->gro_hash[hash].count--;
}
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index c9993c6c2fd4..9d4e56d97080 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -539,47 +539,17 @@ struct ethtool_link_usettings {
} link_modes;
};
-/* Internal kernel helper to query a device ethtool_link_settings.
- *
- * Backward compatibility note: for compatibility with legacy drivers
- * that implement only the ethtool_cmd API, this has to work with both
- * drivers implementing get_link_ksettings API and drivers
- * implementing get_settings API. When drivers implement get_settings
- * and report ethtool_cmd deprecated fields
- * (transceiver/maxrxpkt/maxtxpkt), these fields are silently ignored
- * because the resulting struct ethtool_link_settings does not report them.
- */
+/* Internal kernel helper to query a device ethtool_link_settings. */
int __ethtool_get_link_ksettings(struct net_device *dev,
struct ethtool_link_ksettings *link_ksettings)
{
- int err;
- struct ethtool_cmd cmd;
-
ASSERT_RTNL();
- if (dev->ethtool_ops->get_link_ksettings) {
- memset(link_ksettings, 0, sizeof(*link_ksettings));
- return dev->ethtool_ops->get_link_ksettings(dev,
- link_ksettings);
- }
-
- /* driver doesn't support %ethtool_link_ksettings API. revert to
- * legacy %ethtool_cmd API, unless it's not supported either.
- * TODO: remove when ethtool_ops::get_settings disappears internally
- */
- if (!dev->ethtool_ops->get_settings)
+ if (!dev->ethtool_ops->get_link_ksettings)
return -EOPNOTSUPP;
- memset(&cmd, 0, sizeof(cmd));
- cmd.cmd = ETHTOOL_GSET;
- err = dev->ethtool_ops->get_settings(dev, &cmd);
- if (err < 0)
- return err;
-
- /* we ignore deprecated fields transceiver/maxrxpkt/maxtxpkt
- */
- convert_legacy_settings_to_link_ksettings(link_ksettings, &cmd);
- return err;
+ memset(link_ksettings, 0, sizeof(*link_ksettings));
+ return dev->ethtool_ops->get_link_ksettings(dev, link_ksettings);
}
EXPORT_SYMBOL(__ethtool_get_link_ksettings);
@@ -635,16 +605,7 @@ store_link_ksettings_for_user(void __user *to,
return 0;
}
-/* Query device for its ethtool_link_settings.
- *
- * Backward compatibility note: this function must fail when driver
- * does not implement ethtool::get_link_ksettings, even if legacy
- * ethtool_ops::get_settings is implemented. This tells new versions
- * of ethtool that they should use the legacy API %ETHTOOL_GSET for
- * this driver, so that they can correctly access the ethtool_cmd
- * deprecated fields (transceiver/maxrxpkt/maxtxpkt), until no driver
- * implements ethtool_ops::get_settings anymore.
- */
+/* Query device for its ethtool_link_settings. */
static int ethtool_get_link_ksettings(struct net_device *dev,
void __user *useraddr)
{
@@ -652,7 +613,6 @@ static int ethtool_get_link_ksettings(struct net_device *dev,
struct ethtool_link_ksettings link_ksettings;
ASSERT_RTNL();
-
if (!dev->ethtool_ops->get_link_ksettings)
return -EOPNOTSUPP;
@@ -699,16 +659,7 @@ static int ethtool_get_link_ksettings(struct net_device *dev,
return store_link_ksettings_for_user(useraddr, &link_ksettings);
}
-/* Update device ethtool_link_settings.
- *
- * Backward compatibility note: this function must fail when driver
- * does not implement ethtool::set_link_ksettings, even if legacy
- * ethtool_ops::set_settings is implemented. This tells new versions
- * of ethtool that they should use the legacy API %ETHTOOL_SSET for
- * this driver, so that they can correctly update the ethtool_cmd
- * deprecated fields (transceiver/maxrxpkt/maxtxpkt), until no driver
- * implements ethtool_ops::get_settings anymore.
- */
+/* Update device ethtool_link_settings. */
static int ethtool_set_link_ksettings(struct net_device *dev,
void __user *useraddr)
{
@@ -746,51 +697,31 @@ static int ethtool_set_link_ksettings(struct net_device *dev,
/* Query device for its ethtool_cmd settings.
*
- * Backward compatibility note: for compatibility with legacy ethtool,
- * this has to work with both drivers implementing get_link_ksettings
- * API and drivers implementing get_settings API. When drivers
- * implement get_link_ksettings and report higher link mode bits, a
- * kernel warning is logged once (with name of 1st driver/device) to
- * recommend user to upgrade ethtool, but the command is successful
- * (only the lower link mode bits reported back to user).
+ * Backward compatibility note: for compatibility with legacy ethtool, this is
+ * now implemented via get_link_ksettings. When driver reports higher link mode
+ * bits, a kernel warning is logged once (with name of 1st driver/device) to
+ * recommend user to upgrade ethtool, but the command is successful (only the
+ * lower link mode bits reported back to user). Deprecated fields from
+ * ethtool_cmd (transceiver/maxrxpkt/maxtxpkt) are always set to zero.
*/
static int ethtool_get_settings(struct net_device *dev, void __user *useraddr)
{
+ struct ethtool_link_ksettings link_ksettings;
struct ethtool_cmd cmd;
+ int err;
ASSERT_RTNL();
+ if (!dev->ethtool_ops->get_link_ksettings)
+ return -EOPNOTSUPP;
- if (dev->ethtool_ops->get_link_ksettings) {
- /* First, use link_ksettings API if it is supported */
- int err;
- struct ethtool_link_ksettings link_ksettings;
-
- memset(&link_ksettings, 0, sizeof(link_ksettings));
- err = dev->ethtool_ops->get_link_ksettings(dev,
- &link_ksettings);
- if (err < 0)
- return err;
- convert_link_ksettings_to_legacy_settings(&cmd,
- &link_ksettings);
-
- /* send a sensible cmd tag back to user */
- cmd.cmd = ETHTOOL_GSET;
- } else {
- /* driver doesn't support %ethtool_link_ksettings
- * API. revert to legacy %ethtool_cmd API, unless it's
- * not supported either.
- */
- int err;
-
- if (!dev->ethtool_ops->get_settings)
- return -EOPNOTSUPP;
+ memset(&link_ksettings, 0, sizeof(link_ksettings));
+ err = dev->ethtool_ops->get_link_ksettings(dev, &link_ksettings);
+ if (err < 0)
+ return err;
+ convert_link_ksettings_to_legacy_settings(&cmd, &link_ksettings);
- memset(&cmd, 0, sizeof(cmd));
- cmd.cmd = ETHTOOL_GSET;
- err = dev->ethtool_ops->get_settings(dev, &cmd);
- if (err < 0)
- return err;
- }
+ /* send a sensible cmd tag back to user */
+ cmd.cmd = ETHTOOL_GSET;
if (copy_to_user(useraddr, &cmd, sizeof(cmd)))
return -EFAULT;
@@ -800,48 +731,29 @@ static int ethtool_get_settings(struct net_device *dev, void __user *useraddr)
/* Update device link settings with given ethtool_cmd.
*
- * Backward compatibility note: for compatibility with legacy ethtool,
- * this has to work with both drivers implementing set_link_ksettings
- * API and drivers implementing set_settings API. When drivers
- * implement set_link_ksettings and user's request updates deprecated
- * ethtool_cmd fields (transceiver/maxrxpkt/maxtxpkt), a kernel
- * warning is logged once (with name of 1st driver/device) to
- * recommend user to upgrade ethtool, and the request is rejected.
+ * Backward compatibility note: for compatibility with legacy ethtool, this is
+ * now always implemented via set_link_settings. When user's request updates
+ * deprecated ethtool_cmd fields (transceiver/maxrxpkt/maxtxpkt), a kernel
+ * warning is logged once (with name of 1st driver/device) to recommend user to
+ * upgrade ethtool, and the request is rejected.
*/
static int ethtool_set_settings(struct net_device *dev, void __user *useraddr)
{
+ struct ethtool_link_ksettings link_ksettings;
struct ethtool_cmd cmd;
ASSERT_RTNL();
if (copy_from_user(&cmd, useraddr, sizeof(cmd)))
return -EFAULT;
-
- /* first, try new %ethtool_link_ksettings API. */
- if (dev->ethtool_ops->set_link_ksettings) {
- struct ethtool_link_ksettings link_ksettings;
-
- if (!convert_legacy_settings_to_link_ksettings(&link_ksettings,
- &cmd))
- return -EINVAL;
-
- link_ksettings.base.cmd = ETHTOOL_SLINKSETTINGS;
- link_ksettings.base.link_mode_masks_nwords
- = __ETHTOOL_LINK_MODE_MASK_NU32;
- return dev->ethtool_ops->set_link_ksettings(dev,
- &link_ksettings);
- }
-
- /* legacy %ethtool_cmd API */
-
- /* TODO: return -EOPNOTSUPP when ethtool_ops::get_settings
- * disappears internally
- */
-
- if (!dev->ethtool_ops->set_settings)
+ if (!dev->ethtool_ops->set_link_ksettings)
return -EOPNOTSUPP;
- return dev->ethtool_ops->set_settings(dev, &cmd);
+ if (!convert_legacy_settings_to_link_ksettings(&link_ksettings, &cmd))
+ return -EINVAL;
+ link_ksettings.base.link_mode_masks_nwords =
+ __ETHTOOL_LINK_MODE_MASK_NU32;
+ return dev->ethtool_ops->set_link_ksettings(dev, &link_ksettings);
}
static noinline_for_stack int ethtool_get_drvinfo(struct net_device *dev,
diff --git a/net/core/filter.c b/net/core/filter.c
index c25eb36f1320..0b40f95da21b 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2282,14 +2282,21 @@ static const struct bpf_func_proto bpf_msg_cork_bytes_proto = {
.arg2_type = ARG_ANYTHING,
};
+#define sk_msg_iter_var(var) \
+ do { \
+ var++; \
+ if (var == MAX_SKB_FRAGS) \
+ var = 0; \
+ } while (0)
+
BPF_CALL_4(bpf_msg_pull_data,
struct sk_msg_buff *, msg, u32, start, u32, end, u64, flags)
{
- unsigned int len = 0, offset = 0, copy = 0;
+ unsigned int len = 0, offset = 0, copy = 0, poffset = 0;
+ int bytes = end - start, bytes_sg_total;
struct scatterlist *sg = msg->sg_data;
int first_sg, last_sg, i, shift;
unsigned char *p, *to, *from;
- int bytes = end - start;
struct page *page;
if (unlikely(flags || end <= start))
@@ -2299,21 +2306,22 @@ BPF_CALL_4(bpf_msg_pull_data,
i = msg->sg_start;
do {
len = sg[i].length;
- offset += len;
if (start < offset + len)
break;
- i++;
- if (i == MAX_SKB_FRAGS)
- i = 0;
+ offset += len;
+ sk_msg_iter_var(i);
} while (i != msg->sg_end);
if (unlikely(start >= offset + len))
return -EINVAL;
- if (!msg->sg_copy[i] && bytes <= len)
- goto out;
-
first_sg = i;
+ /* The start may point into the sg element so we need to also
+ * account for the headroom.
+ */
+ bytes_sg_total = start - offset + bytes;
+ if (!msg->sg_copy[i] && bytes_sg_total <= len)
+ goto out;
/* At this point we need to linearize multiple scatterlist
* elements or a single shared page. Either way we need to
@@ -2327,37 +2335,33 @@ BPF_CALL_4(bpf_msg_pull_data,
*/
do {
copy += sg[i].length;
- i++;
- if (i == MAX_SKB_FRAGS)
- i = 0;
- if (bytes < copy)
+ sk_msg_iter_var(i);
+ if (bytes_sg_total <= copy)
break;
} while (i != msg->sg_end);
last_sg = i;
- if (unlikely(copy < end - start))
+ if (unlikely(bytes_sg_total > copy))
return -EINVAL;
- page = alloc_pages(__GFP_NOWARN | GFP_ATOMIC, get_order(copy));
+ page = alloc_pages(__GFP_NOWARN | GFP_ATOMIC | __GFP_COMP,
+ get_order(copy));
if (unlikely(!page))
return -ENOMEM;
p = page_address(page);
- offset = 0;
i = first_sg;
do {
from = sg_virt(&sg[i]);
len = sg[i].length;
- to = p + offset;
+ to = p + poffset;
memcpy(to, from, len);
- offset += len;
+ poffset += len;
sg[i].length = 0;
put_page(sg_page(&sg[i]));
- i++;
- if (i == MAX_SKB_FRAGS)
- i = 0;
+ sk_msg_iter_var(i);
} while (i != last_sg);
sg[first_sg].length = copy;
@@ -2367,11 +2371,15 @@ BPF_CALL_4(bpf_msg_pull_data,
* had a single entry though we can just replace it and
* be done. Otherwise walk the ring and shift the entries.
*/
- shift = last_sg - first_sg - 1;
+ WARN_ON_ONCE(last_sg == first_sg);
+ shift = last_sg > first_sg ?
+ last_sg - first_sg - 1 :
+ MAX_SKB_FRAGS - first_sg + last_sg - 1;
if (!shift)
goto out;
- i = first_sg + 1;
+ i = first_sg;
+ sk_msg_iter_var(i);
do {
int move_from;
@@ -2388,15 +2396,13 @@ BPF_CALL_4(bpf_msg_pull_data,
sg[move_from].page_link = 0;
sg[move_from].offset = 0;
- i++;
- if (i == MAX_SKB_FRAGS)
- i = 0;
+ sk_msg_iter_var(i);
} while (1);
msg->sg_end -= shift;
if (msg->sg_end < 0)
msg->sg_end += MAX_SKB_FRAGS;
out:
- msg->data = sg_virt(&sg[i]) + start - offset;
+ msg->data = sg_virt(&sg[first_sg]) + start - offset;
msg->data_end = msg->data + bytes;
return 0;
@@ -4007,6 +4013,12 @@ BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock,
tp->snd_ssthresh = val;
}
break;
+ case TCP_SAVE_SYN:
+ if (val < 0 || val > 1)
+ ret = -EINVAL;
+ else
+ tp->save_syn = val;
+ break;
default:
ret = -EINVAL;
}
@@ -4032,21 +4044,32 @@ static const struct bpf_func_proto bpf_setsockopt_proto = {
BPF_CALL_5(bpf_getsockopt, struct bpf_sock_ops_kern *, bpf_sock,
int, level, int, optname, char *, optval, int, optlen)
{
+ struct inet_connection_sock *icsk;
struct sock *sk = bpf_sock->sk;
+ struct tcp_sock *tp;
if (!sk_fullsock(sk))
goto err_clear;
-
#ifdef CONFIG_INET
if (level == SOL_TCP && sk->sk_prot->getsockopt == tcp_getsockopt) {
- if (optname == TCP_CONGESTION) {
- struct inet_connection_sock *icsk = inet_csk(sk);
+ switch (optname) {
+ case TCP_CONGESTION:
+ icsk = inet_csk(sk);
if (!icsk->icsk_ca_ops || optlen <= 1)
goto err_clear;
strncpy(optval, icsk->icsk_ca_ops->name, optlen);
optval[optlen - 1] = 0;
- } else {
+ break;
+ case TCP_SAVED_SYN:
+ tp = tcp_sk(sk);
+
+ if (optlen <= 0 || !tp->saved_syn ||
+ optlen > tp->saved_syn[0])
+ goto err_clear;
+ memcpy(optval, tp->saved_syn + 1, optlen);
+ break;
+ default:
goto err_clear;
}
} else if (level == SOL_IP) {
@@ -7281,7 +7304,7 @@ static u32 sk_reuseport_convert_ctx_access(enum bpf_access_type type,
break;
case offsetof(struct sk_reuseport_md, ip_protocol):
- BUILD_BUG_ON(hweight_long(SK_FL_PROTO_MASK) != BITS_PER_BYTE);
+ BUILD_BUG_ON(HWEIGHT32(SK_FL_PROTO_MASK) != BITS_PER_BYTE);
SK_REUSEPORT_LOAD_SK_FIELD_SIZE_OFF(__sk_flags_offset,
BPF_W, 0);
*insn++ = BPF_ALU32_IMM(BPF_AND, si->dst_reg, SK_FL_PROTO_MASK);
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index aa19d86937af..91592fceeaad 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -1180,6 +1180,12 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new,
lladdr = neigh->ha;
}
+ /* Update confirmed timestamp for neighbour entry after we
+ * received ARP packet even if it doesn't change IP to MAC binding.
+ */
+ if (new & NUD_CONNECTED)
+ neigh->confirmed = jiffies;
+
/* If entry was valid and address is not changed,
do not change entry state, if new one is STALE.
*/
@@ -1201,15 +1207,12 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new,
}
}
- /* Update timestamps only once we know we will make a change to the
+ /* Update timestamp only once we know we will make a change to the
* neighbour entry. Otherwise we risk to move the locktime window with
* noop updates and ignore relevant ARP updates.
*/
- if (new != old || lladdr != neigh->ha) {
- if (new & NUD_CONNECTED)
- neigh->confirmed = jiffies;
+ if (new != old || lladdr != neigh->ha)
neigh->updated = jiffies;
- }
if (new != old) {
neigh_del_timer(neigh);
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 7f6938405fa1..6ac919847ce6 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -3426,7 +3426,7 @@ xmit_more:
net_info_ratelimited("%s xmit error: %d\n",
pkt_dev->odevname, ret);
pkt_dev->errors++;
- /* fallthru */
+ /* fall through */
case NETDEV_TX_BUSY:
/* Retry it next time */
refcount_dec(&(pkt_dev->skb->users));
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 24431e578310..80a7e18c65fb 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -324,6 +324,10 @@ void rtnl_unregister_all(int protocol)
rtnl_lock();
tab = rtnl_msg_handlers[protocol];
+ if (!tab) {
+ rtnl_unlock();
+ return;
+ }
RCU_INIT_POINTER(rtnl_msg_handlers[protocol], NULL);
for (msgindex = 0; msgindex < RTM_NR_MSGTYPES; msgindex++) {
link = tab[msgindex];
@@ -1012,7 +1016,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev,
+ nla_total_size(4) /* IFLA_NEW_NETNSID */
+ nla_total_size(4) /* IFLA_NEW_IFINDEX */
+ nla_total_size(1) /* IFLA_PROTO_DOWN */
- + nla_total_size(4) /* IFLA_IF_NETNSID */
+ + nla_total_size(4) /* IFLA_TARGET_NETNSID */
+ nla_total_size(4) /* IFLA_CARRIER_UP_COUNT */
+ nla_total_size(4) /* IFLA_CARRIER_DOWN_COUNT */
+ nla_total_size(4) /* IFLA_MIN_MTU */
@@ -1594,7 +1598,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb,
ifm->ifi_flags = dev_get_flags(dev);
ifm->ifi_change = change;
- if (tgt_netnsid >= 0 && nla_put_s32(skb, IFLA_IF_NETNSID, tgt_netnsid))
+ if (tgt_netnsid >= 0 && nla_put_s32(skb, IFLA_TARGET_NETNSID, tgt_netnsid))
goto nla_put_failure;
if (nla_put_string(skb, IFLA_IFNAME, dev->name) ||
@@ -1733,7 +1737,7 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = {
[IFLA_XDP] = { .type = NLA_NESTED },
[IFLA_EVENT] = { .type = NLA_U32 },
[IFLA_GROUP] = { .type = NLA_U32 },
- [IFLA_IF_NETNSID] = { .type = NLA_S32 },
+ [IFLA_TARGET_NETNSID] = { .type = NLA_S32 },
[IFLA_CARRIER_UP_COUNT] = { .type = NLA_U32 },
[IFLA_CARRIER_DOWN_COUNT] = { .type = NLA_U32 },
[IFLA_MIN_MTU] = { .type = NLA_U32 },
@@ -1841,7 +1845,15 @@ static bool link_dump_filtered(struct net_device *dev,
return false;
}
-static struct net *get_target_net(struct sock *sk, int netnsid)
+/**
+ * rtnl_get_net_ns_capable - Get netns if sufficiently privileged.
+ * @sk: netlink socket
+ * @netnsid: network namespace identifier
+ *
+ * Returns the network namespace identified by netnsid on success or an error
+ * pointer on failure.
+ */
+struct net *rtnl_get_net_ns_capable(struct sock *sk, int netnsid)
{
struct net *net;
@@ -1858,6 +1870,7 @@ static struct net *get_target_net(struct sock *sk, int netnsid)
}
return net;
}
+EXPORT_SYMBOL_GPL(rtnl_get_net_ns_capable);
static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
{
@@ -1891,9 +1904,9 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
if (nlmsg_parse(cb->nlh, hdrlen, tb, IFLA_MAX,
ifla_policy, NULL) >= 0) {
- if (tb[IFLA_IF_NETNSID]) {
- netnsid = nla_get_s32(tb[IFLA_IF_NETNSID]);
- tgt_net = get_target_net(skb->sk, netnsid);
+ if (tb[IFLA_TARGET_NETNSID]) {
+ netnsid = nla_get_s32(tb[IFLA_TARGET_NETNSID]);
+ tgt_net = rtnl_get_net_ns_capable(skb->sk, netnsid);
if (IS_ERR(tgt_net)) {
tgt_net = net;
netnsid = -1;
@@ -1980,7 +1993,7 @@ EXPORT_SYMBOL(rtnl_link_get_net);
*
* 1. IFLA_NET_NS_PID
* 2. IFLA_NET_NS_FD
- * 3. IFLA_IF_NETNSID
+ * 3. IFLA_TARGET_NETNSID
*/
static struct net *rtnl_link_get_net_by_nlattr(struct net *src_net,
struct nlattr *tb[])
@@ -1990,10 +2003,10 @@ static struct net *rtnl_link_get_net_by_nlattr(struct net *src_net,
if (tb[IFLA_NET_NS_PID] || tb[IFLA_NET_NS_FD])
return rtnl_link_get_net(src_net, tb);
- if (!tb[IFLA_IF_NETNSID])
+ if (!tb[IFLA_TARGET_NETNSID])
return get_net(src_net);
- net = get_net_ns_by_id(src_net, nla_get_u32(tb[IFLA_IF_NETNSID]));
+ net = get_net_ns_by_id(src_net, nla_get_u32(tb[IFLA_TARGET_NETNSID]));
if (!net)
return ERR_PTR(-EINVAL);
@@ -2034,13 +2047,13 @@ static int rtnl_ensure_unique_netns(struct nlattr *tb[],
return -EOPNOTSUPP;
}
- if (tb[IFLA_IF_NETNSID] && (tb[IFLA_NET_NS_PID] || tb[IFLA_NET_NS_FD]))
+ if (tb[IFLA_TARGET_NETNSID] && (tb[IFLA_NET_NS_PID] || tb[IFLA_NET_NS_FD]))
goto invalid_attr;
- if (tb[IFLA_NET_NS_PID] && (tb[IFLA_IF_NETNSID] || tb[IFLA_NET_NS_FD]))
+ if (tb[IFLA_NET_NS_PID] && (tb[IFLA_TARGET_NETNSID] || tb[IFLA_NET_NS_FD]))
goto invalid_attr;
- if (tb[IFLA_NET_NS_FD] && (tb[IFLA_IF_NETNSID] || tb[IFLA_NET_NS_PID]))
+ if (tb[IFLA_NET_NS_FD] && (tb[IFLA_TARGET_NETNSID] || tb[IFLA_NET_NS_PID]))
goto invalid_attr;
return 0;
@@ -2316,7 +2329,7 @@ static int do_setlink(const struct sk_buff *skb,
if (err < 0)
return err;
- if (tb[IFLA_NET_NS_PID] || tb[IFLA_NET_NS_FD] || tb[IFLA_IF_NETNSID]) {
+ 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);
if (IS_ERR(net)) {
@@ -2759,9 +2772,9 @@ static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh,
if (tb[IFLA_IFNAME])
nla_strlcpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ);
- if (tb[IFLA_IF_NETNSID]) {
- netnsid = nla_get_s32(tb[IFLA_IF_NETNSID]);
- tgt_net = get_target_net(NETLINK_CB(skb).sk, netnsid);
+ if (tb[IFLA_TARGET_NETNSID]) {
+ netnsid = nla_get_s32(tb[IFLA_TARGET_NETNSID]);
+ tgt_net = rtnl_get_net_ns_capable(NETLINK_CB(skb).sk, netnsid);
if (IS_ERR(tgt_net))
return PTR_ERR(tgt_net);
}
@@ -2806,7 +2819,7 @@ int rtnl_configure_link(struct net_device *dev, const struct ifinfomsg *ifm)
}
if (dev->rtnl_link_state == RTNL_LINK_INITIALIZED) {
- __dev_notify_flags(dev, old_flags, 0U);
+ __dev_notify_flags(dev, old_flags, (old_flags ^ dev->flags));
} else {
dev->rtnl_link_state = RTNL_LINK_INITIALIZED;
__dev_notify_flags(dev, old_flags, ~0U);
@@ -3169,9 +3182,9 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr *nlh,
if (err < 0)
return err;
- if (tb[IFLA_IF_NETNSID]) {
- netnsid = nla_get_s32(tb[IFLA_IF_NETNSID]);
- tgt_net = get_target_net(NETLINK_CB(skb).sk, netnsid);
+ if (tb[IFLA_TARGET_NETNSID]) {
+ netnsid = nla_get_s32(tb[IFLA_TARGET_NETNSID]);
+ tgt_net = rtnl_get_net_ns_capable(NETLINK_CB(skb).sk, netnsid);
if (IS_ERR(tgt_net))
return PTR_ERR(tgt_net);
}
@@ -3256,13 +3269,13 @@ static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb)
{
int idx;
int s_idx = cb->family;
+ int type = cb->nlh->nlmsg_type - RTM_BASE;
if (s_idx == 0)
s_idx = 1;
for (idx = 1; idx <= RTNL_FAMILY_MAX; idx++) {
struct rtnl_link **tab;
- int type = cb->nlh->nlmsg_type-RTM_BASE;
struct rtnl_link *link;
rtnl_dumpit_func dumpit;
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index c996c09d095f..b2c807f67aba 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -939,9 +939,6 @@ struct ubuf_info *sock_zerocopy_alloc(struct sock *sk, size_t size)
WARN_ON_ONCE(!in_task());
- if (!sock_flag(sk, SOCK_ZEROCOPY))
- return NULL;
-
skb = sock_omalloc(sk, 0, GFP_KERNEL);
if (!skb)
return NULL;
diff --git a/net/core/sock.c b/net/core/sock.c
index 3730eb855095..8537b6ca72c5 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2332,7 +2332,7 @@ static void __release_sock(struct sock *sk)
next = skb->next;
prefetch(next);
WARN_ON_ONCE(skb_dst_is_noref(skb));
- skb->next = NULL;
+ skb_mark_not_on_list(skb);
sk_backlog_rcv(sk, skb);
cond_resched();
diff --git a/net/core/xdp.c b/net/core/xdp.c
index 89b6785cef2a..4b2b194f4f1f 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -94,11 +94,21 @@ static void __xdp_mem_allocator_rcu_free(struct rcu_head *rcu)
kfree(xa);
}
-static void __xdp_rxq_info_unreg_mem_model(struct xdp_rxq_info *xdp_rxq)
+void xdp_rxq_info_unreg_mem_model(struct xdp_rxq_info *xdp_rxq)
{
struct xdp_mem_allocator *xa;
int id = xdp_rxq->mem.id;
+ if (xdp_rxq->reg_state != REG_STATE_REGISTERED) {
+ WARN(1, "Missing register, driver bug");
+ return;
+ }
+
+ if (xdp_rxq->mem.type != MEM_TYPE_PAGE_POOL &&
+ xdp_rxq->mem.type != MEM_TYPE_ZERO_COPY) {
+ return;
+ }
+
if (id == 0)
return;
@@ -110,6 +120,7 @@ static void __xdp_rxq_info_unreg_mem_model(struct xdp_rxq_info *xdp_rxq)
mutex_unlock(&mem_id_lock);
}
+EXPORT_SYMBOL_GPL(xdp_rxq_info_unreg_mem_model);
void xdp_rxq_info_unreg(struct xdp_rxq_info *xdp_rxq)
{
@@ -119,7 +130,7 @@ void xdp_rxq_info_unreg(struct xdp_rxq_info *xdp_rxq)
WARN(!(xdp_rxq->reg_state == REG_STATE_REGISTERED), "Driver BUG");
- __xdp_rxq_info_unreg_mem_model(xdp_rxq);
+ xdp_rxq_info_unreg_mem_model(xdp_rxq);
xdp_rxq->reg_state = REG_STATE_UNREGISTERED;
xdp_rxq->dev = NULL;
@@ -398,3 +409,41 @@ void xdp_attachment_setup(struct xdp_attachment_info *info,
info->flags = bpf->flags;
}
EXPORT_SYMBOL_GPL(xdp_attachment_setup);
+
+struct xdp_frame *xdp_convert_zc_to_xdp_frame(struct xdp_buff *xdp)
+{
+ unsigned int metasize, totsize;
+ void *addr, *data_to_copy;
+ struct xdp_frame *xdpf;
+ struct page *page;
+
+ /* Clone into a MEM_TYPE_PAGE_ORDER0 xdp_frame. */
+ metasize = xdp_data_meta_unsupported(xdp) ? 0 :
+ xdp->data - xdp->data_meta;
+ totsize = xdp->data_end - xdp->data + metasize;
+
+ if (sizeof(*xdpf) + totsize > PAGE_SIZE)
+ return NULL;
+
+ page = dev_alloc_page();
+ if (!page)
+ return NULL;
+
+ addr = page_to_virt(page);
+ xdpf = addr;
+ memset(xdpf, 0, sizeof(*xdpf));
+
+ addr += sizeof(*xdpf);
+ data_to_copy = metasize ? xdp->data_meta : xdp->data;
+ memcpy(addr, data_to_copy, totsize);
+
+ xdpf->data = addr + metasize;
+ xdpf->len = totsize - metasize;
+ xdpf->headroom = 0;
+ xdpf->metasize = metasize;
+ xdpf->mem.type = MEM_TYPE_PAGE_ORDER0;
+
+ xdp_return_buff(xdp);
+ return xdpf;
+}
+EXPORT_SYMBOL_GPL(xdp_convert_zc_to_xdp_frame);
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.