summaryrefslogtreecommitdiff
path: root/net/core
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2018-12-27 13:04:52 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2018-12-27 13:04:52 -0800
commite0c38a4d1f196a4b17d2eba36afff8f656a4f1de (patch)
treeb26a69fabef0160adb127416a9744217700feeb7 /net/core
parent7f9f852c75e7d776b078813586c76a2bc7dca993 (diff)
parent90cadbbf341dd5b2df991c33a6bd6341f3a53788 (diff)
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
Pull networking updates from David Miller: 1) New ipset extensions for matching on destination MAC addresses, from Stefano Brivio. 2) Add ipv4 ttl and tos, plus ipv6 flow label and hop limit offloads to nfp driver. From Stefano Brivio. 3) Implement GRO for plain UDP sockets, from Paolo Abeni. 4) Lots of work from Michał Mirosław to eliminate the VLAN_TAG_PRESENT bit so that we could support the entire vlan_tci value. 5) Rework the IPSEC policy lookups to better optimize more usecases, from Florian Westphal. 6) Infrastructure changes eliminating direct manipulation of SKB lists wherever possible, and to always use the appropriate SKB list helpers. This work is still ongoing... 7) Lots of PHY driver and state machine improvements and simplifications, from Heiner Kallweit. 8) Various TSO deferral refinements, from Eric Dumazet. 9) Add ntuple filter support to aquantia driver, from Dmitry Bogdanov. 10) Batch dropping of XDP packets in tuntap, from Jason Wang. 11) Lots of cleanups and improvements to the r8169 driver from Heiner Kallweit, including support for ->xmit_more. This driver has been getting some much needed love since he started working on it. 12) Lots of new forwarding selftests from Petr Machata. 13) Enable VXLAN learning in mlxsw driver, from Ido Schimmel. 14) Packed ring support for virtio, from Tiwei Bie. 15) Add new Aquantia AQtion USB driver, from Dmitry Bezrukov. 16) Add XDP support to dpaa2-eth driver, from Ioana Ciocoi Radulescu. 17) Implement coalescing on TCP backlog queue, from Eric Dumazet. 18) Implement carrier change in tun driver, from Nicolas Dichtel. 19) Support msg_zerocopy in UDP, from Willem de Bruijn. 20) Significantly improve garbage collection of neighbor objects when the table has many PERMANENT entries, from David Ahern. 21) Remove egdev usage from nfp and mlx5, and remove the facility completely from the tree as it no longer has any users. From Oz Shlomo and others. 22) Add a NETDEV_PRE_CHANGEADDR so that drivers can veto the change and therefore abort the operation before the commit phase (which is the NETDEV_CHANGEADDR event). From Petr Machata. 23) Add indirect call wrappers to avoid retpoline overhead, and use them in the GRO code paths. From Paolo Abeni. 24) Add support for netlink FDB get operations, from Roopa Prabhu. 25) Support bloom filter in mlxsw driver, from Nir Dotan. 26) Add SKB extension infrastructure. This consolidates the handling of the auxiliary SKB data used by IPSEC and bridge netfilter, and is designed to support the needs to MPTCP which could be integrated in the future. 27) Lots of XDP TX optimizations in mlx5 from Tariq Toukan. * git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1845 commits) net: dccp: fix kernel crash on module load drivers/net: appletalk/cops: remove redundant if statement and mask bnx2x: Fix NULL pointer dereference in bnx2x_del_all_vlans() on some hw net/net_namespace: Check the return value of register_pernet_subsys() net/netlink_compat: Fix a missing check of nla_parse_nested ieee802154: lowpan_header_create check must check daddr net/mlx4_core: drop useless LIST_HEAD mlxsw: spectrum: drop useless LIST_HEAD net/mlx5e: drop useless LIST_HEAD iptunnel: Set tun_flags in the iptunnel_metadata_reply from src net/mlx5e: fix semicolon.cocci warnings staging: octeon: fix build failure with XFRM enabled net: Revert recent Spectre-v1 patches. can: af_can: Fix Spectre v1 vulnerability packet: validate address length if non-zero nfc: af_nfc: Fix Spectre v1 vulnerability phonet: af_phonet: Fix Spectre v1 vulnerability net: core: Fix Spectre v1 vulnerability net: minor cleanup in skb_ext_add() net: drop the unused helper skb_ext_get() ...
Diffstat (limited to 'net/core')
-rw-r--r--net/core/datagram.c45
-rw-r--r--net/core/dev.c152
-rw-r--r--net/core/dev_addr_lists.c100
-rw-r--r--net/core/dev_ioctl.c4
-rw-r--r--net/core/devlink.c5
-rw-r--r--net/core/filter.c455
-rw-r--r--net/core/flow_dissector.c3
-rw-r--r--net/core/neighbour.c448
-rw-r--r--net/core/net-sysfs.c2
-rw-r--r--net/core/net_namespace.c162
-rw-r--r--net/core/netpoll.c2
-rw-r--r--net/core/rtnetlink.c517
-rw-r--r--net/core/skbuff.c313
-rw-r--r--net/core/skmsg.c23
-rw-r--r--net/core/sock.c14
-rw-r--r--net/core/sock_reuseport.c1
-rw-r--r--net/core/stream.c2
17 files changed, 1790 insertions, 458 deletions
diff --git a/net/core/datagram.c b/net/core/datagram.c
index 57f3a6fcfc1e..4bf62b1afa3b 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -728,49 +728,6 @@ fault:
return -EFAULT;
}
-__sum16 __skb_checksum_complete_head(struct sk_buff *skb, int len)
-{
- __sum16 sum;
-
- sum = csum_fold(skb_checksum(skb, 0, len, skb->csum));
- if (likely(!sum)) {
- if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE) &&
- !skb->csum_complete_sw)
- netdev_rx_csum_fault(skb->dev);
- }
- if (!skb_shared(skb))
- skb->csum_valid = !sum;
- return sum;
-}
-EXPORT_SYMBOL(__skb_checksum_complete_head);
-
-__sum16 __skb_checksum_complete(struct sk_buff *skb)
-{
- __wsum csum;
- __sum16 sum;
-
- csum = skb_checksum(skb, 0, skb->len, 0);
-
- /* skb->csum holds pseudo checksum */
- sum = csum_fold(csum_add(skb->csum, csum));
- if (likely(!sum)) {
- if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE) &&
- !skb->csum_complete_sw)
- netdev_rx_csum_fault(skb->dev);
- }
-
- if (!skb_shared(skb)) {
- /* Save full packet checksum */
- skb->csum = csum;
- skb->ip_summed = CHECKSUM_COMPLETE;
- skb->csum_complete_sw = 1;
- skb->csum_valid = !sum;
- }
-
- return sum;
-}
-EXPORT_SYMBOL(__skb_checksum_complete);
-
/**
* skb_copy_and_csum_datagram_msg - Copy and checksum skb to user iovec.
* @skb: skbuff
@@ -810,7 +767,7 @@ int skb_copy_and_csum_datagram_msg(struct sk_buff *skb,
if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE) &&
!skb->csum_complete_sw)
- netdev_rx_csum_fault(NULL);
+ netdev_rx_csum_fault(NULL, skb);
}
return 0;
fault:
diff --git a/net/core/dev.c b/net/core/dev.c
index 722d50dbf8a4..1b5a4410be0e 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -145,6 +145,7 @@
#include <linux/sctp.h>
#include <net/udp_tunnel.h>
#include <linux/net_namespace.h>
+#include <linux/indirect_call_wrapper.h>
#include "net-sysfs.h"
@@ -162,6 +163,9 @@ static struct list_head offload_base __read_mostly;
static int netif_rx_internal(struct sk_buff *skb);
static int call_netdevice_notifiers_info(unsigned long val,
struct netdev_notifier_info *info);
+static int call_netdevice_notifiers_extack(unsigned long val,
+ struct net_device *dev,
+ struct netlink_ext_ack *extack);
static struct napi_struct *napi_by_id(unsigned int napi_id);
/*
@@ -1361,7 +1365,7 @@ void netdev_notify_peers(struct net_device *dev)
}
EXPORT_SYMBOL(netdev_notify_peers);
-static int __dev_open(struct net_device *dev)
+static int __dev_open(struct net_device *dev, struct netlink_ext_ack *extack)
{
const struct net_device_ops *ops = dev->netdev_ops;
int ret;
@@ -1377,7 +1381,7 @@ static int __dev_open(struct net_device *dev)
*/
netpoll_poll_disable(dev);
- ret = call_netdevice_notifiers(NETDEV_PRE_UP, dev);
+ ret = call_netdevice_notifiers_extack(NETDEV_PRE_UP, dev, extack);
ret = notifier_to_errno(ret);
if (ret)
return ret;
@@ -1406,7 +1410,8 @@ static int __dev_open(struct net_device *dev)
/**
* dev_open - prepare an interface for use.
- * @dev: device to open
+ * @dev: device to open
+ * @extack: netlink extended ack
*
* Takes a device from down to up state. The device's private open
* function is invoked and then the multicast lists are loaded. Finally
@@ -1416,14 +1421,14 @@ static int __dev_open(struct net_device *dev)
* Calling this function on an active interface is a nop. On a failure
* a negative errno code is returned.
*/
-int dev_open(struct net_device *dev)
+int dev_open(struct net_device *dev, struct netlink_ext_ack *extack)
{
int ret;
if (dev->flags & IFF_UP)
return 0;
- ret = __dev_open(dev);
+ ret = __dev_open(dev, extack);
if (ret < 0)
return ret;
@@ -1585,6 +1590,7 @@ const char *netdev_cmd_to_name(enum netdev_cmd cmd)
N(UDP_TUNNEL_DROP_INFO) N(CHANGE_TX_QUEUE_LEN)
N(CVLAN_FILTER_PUSH_INFO) N(CVLAN_FILTER_DROP_INFO)
N(SVLAN_FILTER_PUSH_INFO) N(SVLAN_FILTER_DROP_INFO)
+ N(PRE_CHANGEADDR)
}
#undef N
return "UNKNOWN_NETDEV_EVENT";
@@ -1733,6 +1739,18 @@ static int call_netdevice_notifiers_info(unsigned long val,
return raw_notifier_call_chain(&netdev_chain, val, info);
}
+static int call_netdevice_notifiers_extack(unsigned long val,
+ struct net_device *dev,
+ struct netlink_ext_ack *extack)
+{
+ struct netdev_notifier_info info = {
+ .dev = dev,
+ .extack = extack,
+ };
+
+ return call_netdevice_notifiers_info(val, &info);
+}
+
/**
* call_netdevice_notifiers - call all network notifier blocks
* @val: value passed unmodified to notifier function
@@ -1744,11 +1762,7 @@ static int call_netdevice_notifiers_info(unsigned long val,
int call_netdevice_notifiers(unsigned long val, struct net_device *dev)
{
- struct netdev_notifier_info info = {
- .dev = dev,
- };
-
- return call_netdevice_notifiers_info(val, &info);
+ return call_netdevice_notifiers_extack(val, dev, NULL);
}
EXPORT_SYMBOL(call_netdevice_notifiers);
@@ -3096,10 +3110,17 @@ EXPORT_SYMBOL(__skb_gso_segment);
/* Take action when hardware reception checksum errors are detected. */
#ifdef CONFIG_BUG
-void netdev_rx_csum_fault(struct net_device *dev)
+void netdev_rx_csum_fault(struct net_device *dev, struct sk_buff *skb)
{
if (net_ratelimit()) {
pr_err("%s: hw csum failure\n", dev ? dev->name : "<unknown>");
+ if (dev)
+ pr_err("dev features: %pNF\n", &dev->features);
+ pr_err("skb len=%u data_len=%u pkt_type=%u gso_size=%u gso_type=%u nr_frags=%u ip_summed=%u csum=%x csum_complete_sw=%d csum_valid=%d csum_level=%u\n",
+ skb->len, skb->data_len, skb->pkt_type,
+ skb_shinfo(skb)->gso_size, skb_shinfo(skb)->gso_type,
+ skb_shinfo(skb)->nr_frags, skb->ip_summed, skb->csum,
+ skb->csum_complete_sw, skb->csum_valid, skb->csum_level);
dump_stack();
}
}
@@ -4525,9 +4546,14 @@ static int netif_rx_internal(struct sk_buff *skb)
int netif_rx(struct sk_buff *skb)
{
+ int ret;
+
trace_netif_rx_entry(skb);
- return netif_rx_internal(skb);
+ ret = netif_rx_internal(skb);
+ trace_netif_rx_exit(ret);
+
+ return ret;
}
EXPORT_SYMBOL(netif_rx);
@@ -4542,6 +4568,7 @@ int netif_rx_ni(struct sk_buff *skb)
if (local_softirq_pending())
do_softirq();
preempt_enable();
+ trace_netif_rx_ni_exit(err);
return err;
}
@@ -4894,7 +4921,7 @@ skip_classify:
* and set skb->priority like in vlan_do_receive()
* For the time being, just ignore Priority Code Point
*/
- skb->vlan_tci = 0;
+ __vlan_hwaccel_clear_tag(skb);
}
type = skb->protocol;
@@ -5227,9 +5254,14 @@ static void netif_receive_skb_list_internal(struct list_head *head)
*/
int netif_receive_skb(struct sk_buff *skb)
{
+ int ret;
+
trace_netif_receive_skb_entry(skb);
- return netif_receive_skb_internal(skb);
+ ret = netif_receive_skb_internal(skb);
+ trace_netif_receive_skb_exit(ret);
+
+ return ret;
}
EXPORT_SYMBOL(netif_receive_skb);
@@ -5249,9 +5281,12 @@ void netif_receive_skb_list(struct list_head *head)
if (list_empty(head))
return;
- list_for_each_entry(skb, head, list)
- trace_netif_receive_skb_list_entry(skb);
+ if (trace_netif_receive_skb_list_entry_enabled()) {
+ list_for_each_entry(skb, head, list)
+ trace_netif_receive_skb_list_entry(skb);
+ }
netif_receive_skb_list_internal(head);
+ trace_netif_receive_skb_list_exit(0);
}
EXPORT_SYMBOL(netif_receive_skb_list);
@@ -5304,6 +5339,8 @@ static void flush_all_backlogs(void)
put_online_cpus();
}
+INDIRECT_CALLABLE_DECLARE(int inet_gro_complete(struct sk_buff *, int));
+INDIRECT_CALLABLE_DECLARE(int ipv6_gro_complete(struct sk_buff *, int));
static int napi_gro_complete(struct sk_buff *skb)
{
struct packet_offload *ptype;
@@ -5323,7 +5360,9 @@ static int napi_gro_complete(struct sk_buff *skb)
if (ptype->type != type || !ptype->callbacks.gro_complete)
continue;
- err = ptype->callbacks.gro_complete(skb, 0);
+ err = INDIRECT_CALL_INET(ptype->callbacks.gro_complete,
+ ipv6_gro_complete, inet_gro_complete,
+ skb, 0);
break;
}
rcu_read_unlock();
@@ -5362,11 +5401,13 @@ static void __napi_gro_flush_chain(struct napi_struct *napi, u32 index,
*/
void napi_gro_flush(struct napi_struct *napi, bool flush_old)
{
- u32 i;
+ unsigned long bitmask = napi->gro_bitmask;
+ unsigned int i, base = ~0U;
- for (i = 0; i < GRO_HASH_BUCKETS; i++) {
- if (test_bit(i, &napi->gro_bitmask))
- __napi_gro_flush_chain(napi, i, flush_old);
+ while ((i = ffs(bitmask)) != 0) {
+ bitmask >>= i;
+ base += i;
+ __napi_gro_flush_chain(napi, base, flush_old);
}
}
EXPORT_SYMBOL(napi_gro_flush);
@@ -5391,7 +5432,9 @@ static struct list_head *gro_list_prepare(struct napi_struct *napi,
}
diffs = (unsigned long)p->dev ^ (unsigned long)skb->dev;
- diffs |= p->vlan_tci ^ skb->vlan_tci;
+ diffs |= skb_vlan_tag_present(p) ^ skb_vlan_tag_present(skb);
+ if (skb_vlan_tag_present(p))
+ diffs |= p->vlan_tci ^ skb->vlan_tci;
diffs |= skb_metadata_dst_cmp(p, skb);
diffs |= skb_metadata_differs(p, skb);
if (maclen == ETH_HLEN)
@@ -5466,6 +5509,10 @@ static void gro_flush_oldest(struct list_head *head)
napi_gro_complete(oldest);
}
+INDIRECT_CALLABLE_DECLARE(struct sk_buff *inet_gro_receive(struct list_head *,
+ struct sk_buff *));
+INDIRECT_CALLABLE_DECLARE(struct sk_buff *ipv6_gro_receive(struct list_head *,
+ struct sk_buff *));
static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
{
u32 hash = skb_get_hash_raw(skb) & (GRO_HASH_BUCKETS - 1);
@@ -5515,7 +5562,9 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
NAPI_GRO_CB(skb)->csum_valid = 0;
}
- pp = ptype->callbacks.gro_receive(gro_head, skb);
+ pp = INDIRECT_CALL_INET(ptype->callbacks.gro_receive,
+ ipv6_gro_receive, inet_gro_receive,
+ gro_head, skb);
break;
}
rcu_read_unlock();
@@ -5639,12 +5688,17 @@ static gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb)
gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
{
+ gro_result_t ret;
+
skb_mark_napi_id(skb, napi);
trace_napi_gro_receive_entry(skb);
skb_gro_reset_offset(skb);
- return napi_skb_finish(dev_gro_receive(napi, skb), skb);
+ ret = napi_skb_finish(dev_gro_receive(napi, skb), skb);
+ trace_napi_gro_receive_exit(ret);
+
+ return ret;
}
EXPORT_SYMBOL(napi_gro_receive);
@@ -5657,7 +5711,7 @@ static void napi_reuse_skb(struct napi_struct *napi, struct sk_buff *skb)
__skb_pull(skb, skb_headlen(skb));
/* restore the reserve we had after netdev_alloc_skb_ip_align() */
skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN - skb_headroom(skb));
- skb->vlan_tci = 0;
+ __vlan_hwaccel_clear_tag(skb);
skb->dev = napi->dev;
skb->skb_iif = 0;
@@ -5762,6 +5816,7 @@ static struct sk_buff *napi_frags_skb(struct napi_struct *napi)
gro_result_t napi_gro_frags(struct napi_struct *napi)
{
+ gro_result_t ret;
struct sk_buff *skb = napi_frags_skb(napi);
if (!skb)
@@ -5769,7 +5824,10 @@ gro_result_t napi_gro_frags(struct napi_struct *napi)
trace_napi_gro_frags_entry(skb);
- return napi_frags_finish(napi, skb, dev_gro_receive(napi, skb));
+ ret = napi_frags_finish(napi, skb, dev_gro_receive(napi, skb));
+ trace_napi_gro_frags_exit(ret);
+
+ return ret;
}
EXPORT_SYMBOL(napi_gro_frags);
@@ -5785,10 +5843,11 @@ __sum16 __skb_gro_checksum_complete(struct sk_buff *skb)
/* NAPI_GRO_CB(skb)->csum holds pseudo checksum */
sum = csum_fold(csum_add(NAPI_GRO_CB(skb)->csum, wsum));
+ /* See comments in __skb_checksum_complete(). */
if (likely(!sum)) {
if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE) &&
!skb->csum_complete_sw)
- netdev_rx_csum_fault(skb->dev);
+ netdev_rx_csum_fault(skb->dev, skb);
}
NAPI_GRO_CB(skb)->csum = wsum;
@@ -7467,7 +7526,8 @@ unsigned int dev_get_flags(const struct net_device *dev)
}
EXPORT_SYMBOL(dev_get_flags);
-int __dev_change_flags(struct net_device *dev, unsigned int flags)
+int __dev_change_flags(struct net_device *dev, unsigned int flags,
+ struct netlink_ext_ack *extack)
{
unsigned int old_flags = dev->flags;
int ret;
@@ -7504,7 +7564,7 @@ int __dev_change_flags(struct net_device *dev, unsigned int flags)
if (old_flags & IFF_UP)
__dev_close(dev);
else
- ret = __dev_open(dev);
+ ret = __dev_open(dev, extack);
}
if ((flags ^ dev->gflags) & IFF_PROMISC) {
@@ -7564,16 +7624,18 @@ void __dev_notify_flags(struct net_device *dev, unsigned int old_flags,
* dev_change_flags - change device settings
* @dev: device
* @flags: device state flags
+ * @extack: netlink extended ack
*
* Change settings on device based state flags. The flags are
* in the userspace exported format.
*/
-int dev_change_flags(struct net_device *dev, unsigned int flags)
+int dev_change_flags(struct net_device *dev, unsigned int flags,
+ struct netlink_ext_ack *extack)
{
int ret;
unsigned int changes, old_flags = dev->flags, old_gflags = dev->gflags;
- ret = __dev_change_flags(dev, flags);
+ ret = __dev_change_flags(dev, flags, extack);
if (ret < 0)
return ret;
@@ -7706,13 +7768,36 @@ void dev_set_group(struct net_device *dev, int new_group)
EXPORT_SYMBOL(dev_set_group);
/**
+ * dev_pre_changeaddr_notify - Call NETDEV_PRE_CHANGEADDR.
+ * @dev: device
+ * @addr: new address
+ * @extack: netlink extended ack
+ */
+int dev_pre_changeaddr_notify(struct net_device *dev, const char *addr,
+ struct netlink_ext_ack *extack)
+{
+ struct netdev_notifier_pre_changeaddr_info info = {
+ .info.dev = dev,
+ .info.extack = extack,
+ .dev_addr = addr,
+ };
+ int rc;
+
+ rc = call_netdevice_notifiers_info(NETDEV_PRE_CHANGEADDR, &info.info);
+ return notifier_to_errno(rc);
+}
+EXPORT_SYMBOL(dev_pre_changeaddr_notify);
+
+/**
* dev_set_mac_address - Change Media Access Control Address
* @dev: device
* @sa: new address
+ * @extack: netlink extended ack
*
* Change the hardware (MAC) address of the device
*/
-int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa)
+int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa,
+ struct netlink_ext_ack *extack)
{
const struct net_device_ops *ops = dev->netdev_ops;
int err;
@@ -7723,6 +7808,9 @@ int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa)
return -EINVAL;
if (!netif_device_present(dev))
return -ENODEV;
+ err = dev_pre_changeaddr_notify(dev, sa->sa_data, extack);
+ if (err)
+ return err;
err = ops->ndo_set_mac_address(dev, sa);
if (err)
return err;
diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c
index d884d8f5f0e5..a6723b306717 100644
--- a/net/core/dev_addr_lists.c
+++ b/net/core/dev_addr_lists.c
@@ -278,6 +278,103 @@ int __hw_addr_sync_dev(struct netdev_hw_addr_list *list,
EXPORT_SYMBOL(__hw_addr_sync_dev);
/**
+ * __hw_addr_ref_sync_dev - Synchronize device's multicast address list taking
+ * into account references
+ * @list: address list to synchronize
+ * @dev: device to sync
+ * @sync: function to call if address or reference on it should be added
+ * @unsync: function to call if address or some reference on it should removed
+ *
+ * This function is intended to be called from the ndo_set_rx_mode
+ * function of devices that require explicit address or references on it
+ * add/remove notifications. The unsync function may be NULL in which case
+ * the addresses or references on it requiring removal will simply be
+ * removed without any notification to the device. That is responsibility of
+ * the driver to identify and distribute address or references on it between
+ * internal address tables.
+ **/
+int __hw_addr_ref_sync_dev(struct netdev_hw_addr_list *list,
+ struct net_device *dev,
+ int (*sync)(struct net_device *,
+ const unsigned char *, int),
+ int (*unsync)(struct net_device *,
+ const unsigned char *, int))
+{
+ struct netdev_hw_addr *ha, *tmp;
+ int err, ref_cnt;
+
+ /* first go through and flush out any unsynced/stale entries */
+ list_for_each_entry_safe(ha, tmp, &list->list, list) {
+ /* sync if address is not used */
+ if ((ha->sync_cnt << 1) <= ha->refcount)
+ continue;
+
+ /* if fails defer unsyncing address */
+ ref_cnt = ha->refcount - ha->sync_cnt;
+ if (unsync && unsync(dev, ha->addr, ref_cnt))
+ continue;
+
+ ha->refcount = (ref_cnt << 1) + 1;
+ ha->sync_cnt = ref_cnt;
+ __hw_addr_del_entry(list, ha, false, false);
+ }
+
+ /* go through and sync updated/new entries to the list */
+ list_for_each_entry_safe(ha, tmp, &list->list, list) {
+ /* sync if address added or reused */
+ if ((ha->sync_cnt << 1) >= ha->refcount)
+ continue;
+
+ ref_cnt = ha->refcount - ha->sync_cnt;
+ err = sync(dev, ha->addr, ref_cnt);
+ if (err)
+ return err;
+
+ ha->refcount = ref_cnt << 1;
+ ha->sync_cnt = ref_cnt;
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL(__hw_addr_ref_sync_dev);
+
+/**
+ * __hw_addr_ref_unsync_dev - Remove synchronized addresses and references on
+ * it from device
+ * @list: address list to remove synchronized addresses (references on it) from
+ * @dev: device to sync
+ * @unsync: function to call if address and references on it should be removed
+ *
+ * Remove all addresses that were added to the device by
+ * __hw_addr_ref_sync_dev(). This function is intended to be called from the
+ * ndo_stop or ndo_open functions on devices that require explicit address (or
+ * references on it) add/remove notifications. If the unsync function pointer
+ * is NULL then this function can be used to just reset the sync_cnt for the
+ * addresses in the list.
+ **/
+void __hw_addr_ref_unsync_dev(struct netdev_hw_addr_list *list,
+ struct net_device *dev,
+ int (*unsync)(struct net_device *,
+ const unsigned char *, int))
+{
+ struct netdev_hw_addr *ha, *tmp;
+
+ list_for_each_entry_safe(ha, tmp, &list->list, list) {
+ if (!ha->sync_cnt)
+ continue;
+
+ /* if fails defer unsyncing address */
+ if (unsync && unsync(dev, ha->addr, ha->sync_cnt))
+ continue;
+
+ ha->refcount -= ha->sync_cnt - 1;
+ ha->sync_cnt = 0;
+ __hw_addr_del_entry(list, ha, false, false);
+ }
+}
+EXPORT_SYMBOL(__hw_addr_ref_unsync_dev);
+
+/**
* __hw_addr_unsync_dev - Remove synchronized addresses from device
* @list: address list to remove synchronized addresses from
* @dev: device to sync
@@ -401,6 +498,9 @@ int dev_addr_add(struct net_device *dev, const unsigned char *addr,
ASSERT_RTNL();
+ err = dev_pre_changeaddr_notify(dev, addr, NULL);
+ if (err)
+ return err;
err = __hw_addr_add(&dev->dev_addrs, addr, dev->addr_len, addr_type);
if (!err)
call_netdevice_notifiers(NETDEV_CHANGEADDR, dev);
diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c
index 90e8aa36881e..31380fd5a4e2 100644
--- a/net/core/dev_ioctl.c
+++ b/net/core/dev_ioctl.c
@@ -234,7 +234,7 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, unsigned int cmd)
switch (cmd) {
case SIOCSIFFLAGS: /* Set interface flags */
- return dev_change_flags(dev, ifr->ifr_flags);
+ return dev_change_flags(dev, ifr->ifr_flags, NULL);
case SIOCSIFMETRIC: /* Set the metric on the interface
(currently unused) */
@@ -246,7 +246,7 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, unsigned int cmd)
case SIOCSIFHWADDR:
if (dev->addr_len > sizeof(struct sockaddr))
return -EINVAL;
- return dev_set_mac_address(dev, &ifr->ifr_hwaddr);
+ return dev_set_mac_address(dev, &ifr->ifr_hwaddr, NULL);
case SIOCSIFHWBROADCAST:
if (ifr->ifr_hwaddr.sa_family != dev->type)
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 3a4b29a13d31..abb0da9d7b4b 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -2692,6 +2692,11 @@ static const struct devlink_param devlink_param_generic[] = {
.name = DEVLINK_PARAM_GENERIC_MSIX_VEC_PER_PF_MIN_NAME,
.type = DEVLINK_PARAM_GENERIC_MSIX_VEC_PER_PF_MIN_TYPE,
},
+ {
+ .id = DEVLINK_PARAM_GENERIC_ID_FW_LOAD_POLICY,
+ .name = DEVLINK_PARAM_GENERIC_FW_LOAD_POLICY_NAME,
+ .type = DEVLINK_PARAM_GENERIC_FW_LOAD_POLICY_TYPE,
+ },
};
static int devlink_param_generic_verify(const struct devlink_param *param)
diff --git a/net/core/filter.c b/net/core/filter.c
index 8d2c629501e2..447dd1bad31f 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -296,22 +296,18 @@ static u32 convert_skb_access(int skb_field, int dst_reg, int src_reg,
break;
case SKF_AD_VLAN_TAG:
- case SKF_AD_VLAN_TAG_PRESENT:
BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, vlan_tci) != 2);
- BUILD_BUG_ON(VLAN_TAG_PRESENT != 0x1000);
/* dst_reg = *(u16 *) (src_reg + offsetof(vlan_tci)) */
*insn++ = BPF_LDX_MEM(BPF_H, dst_reg, src_reg,
offsetof(struct sk_buff, vlan_tci));
- if (skb_field == SKF_AD_VLAN_TAG) {
- *insn++ = BPF_ALU32_IMM(BPF_AND, dst_reg,
- ~VLAN_TAG_PRESENT);
- } else {
- /* dst_reg >>= 12 */
- *insn++ = BPF_ALU32_IMM(BPF_RSH, dst_reg, 12);
- /* dst_reg &= 1 */
+ break;
+ case SKF_AD_VLAN_TAG_PRESENT:
+ *insn++ = BPF_LDX_MEM(BPF_B, dst_reg, src_reg, PKT_VLAN_PRESENT_OFFSET());
+ if (PKT_VLAN_PRESENT_BIT)
+ *insn++ = BPF_ALU32_IMM(BPF_RSH, dst_reg, PKT_VLAN_PRESENT_BIT);
+ if (PKT_VLAN_PRESENT_BIT < 7)
*insn++ = BPF_ALU32_IMM(BPF_AND, dst_reg, 1);
- }
break;
}
@@ -467,7 +463,8 @@ static bool convert_bpf_ld_abs(struct sock_filter *fp, struct bpf_insn **insnp)
bool ldx_off_ok = offset <= S16_MAX;
*insn++ = BPF_MOV64_REG(BPF_REG_TMP, BPF_REG_H);
- *insn++ = BPF_ALU64_IMM(BPF_SUB, BPF_REG_TMP, offset);
+ if (offset)
+ *insn++ = BPF_ALU64_IMM(BPF_SUB, BPF_REG_TMP, offset);
*insn++ = BPF_JMP_IMM(BPF_JSLT, BPF_REG_TMP,
size, 2 + endian + (!ldx_off_ok * 2));
if (ldx_off_ok) {
@@ -2428,6 +2425,174 @@ static const struct bpf_func_proto bpf_msg_push_data_proto = {
.arg4_type = ARG_ANYTHING,
};
+static void sk_msg_shift_left(struct sk_msg *msg, int i)
+{
+ int prev;
+
+ do {
+ prev = i;
+ sk_msg_iter_var_next(i);
+ msg->sg.data[prev] = msg->sg.data[i];
+ } while (i != msg->sg.end);
+
+ sk_msg_iter_prev(msg, end);
+}
+
+static void sk_msg_shift_right(struct sk_msg *msg, int i)
+{
+ struct scatterlist tmp, sge;
+
+ sk_msg_iter_next(msg, end);
+ sge = sk_msg_elem_cpy(msg, i);
+ sk_msg_iter_var_next(i);
+ tmp = sk_msg_elem_cpy(msg, i);
+
+ while (i != msg->sg.end) {
+ msg->sg.data[i] = sge;
+ sk_msg_iter_var_next(i);
+ sge = tmp;
+ tmp = sk_msg_elem_cpy(msg, i);
+ }
+}
+
+BPF_CALL_4(bpf_msg_pop_data, struct sk_msg *, msg, u32, start,
+ u32, len, u64, flags)
+{
+ u32 i = 0, l, space, offset = 0;
+ u64 last = start + len;
+ int pop;
+
+ if (unlikely(flags))
+ return -EINVAL;
+
+ /* First find the starting scatterlist element */
+ i = msg->sg.start;
+ do {
+ l = sk_msg_elem(msg, i)->length;
+
+ if (start < offset + l)
+ break;
+ offset += l;
+ sk_msg_iter_var_next(i);
+ } while (i != msg->sg.end);
+
+ /* Bounds checks: start and pop must be inside message */
+ if (start >= offset + l || last >= msg->sg.size)
+ return -EINVAL;
+
+ space = MAX_MSG_FRAGS - sk_msg_elem_used(msg);
+
+ pop = len;
+ /* --------------| offset
+ * -| start |-------- len -------|
+ *
+ * |----- a ----|-------- pop -------|----- b ----|
+ * |______________________________________________| length
+ *
+ *
+ * a: region at front of scatter element to save
+ * b: region at back of scatter element to save when length > A + pop
+ * pop: region to pop from element, same as input 'pop' here will be
+ * decremented below per iteration.
+ *
+ * Two top-level cases to handle when start != offset, first B is non
+ * zero and second B is zero corresponding to when a pop includes more
+ * than one element.
+ *
+ * Then if B is non-zero AND there is no space allocate space and
+ * compact A, B regions into page. If there is space shift ring to
+ * the rigth free'ing the next element in ring to place B, leaving
+ * A untouched except to reduce length.
+ */
+ if (start != offset) {
+ struct scatterlist *nsge, *sge = sk_msg_elem(msg, i);
+ int a = start;
+ int b = sge->length - pop - a;
+
+ sk_msg_iter_var_next(i);
+
+ if (pop < sge->length - a) {
+ if (space) {
+ sge->length = a;
+ sk_msg_shift_right(msg, i);
+ nsge = sk_msg_elem(msg, i);
+ get_page(sg_page(sge));
+ sg_set_page(nsge,
+ sg_page(sge),
+ b, sge->offset + pop + a);
+ } else {
+ struct page *page, *orig;
+ u8 *to, *from;
+
+ page = alloc_pages(__GFP_NOWARN |
+ __GFP_COMP | GFP_ATOMIC,
+ get_order(a + b));
+ if (unlikely(!page))
+ return -ENOMEM;
+
+ sge->length = a;
+ orig = sg_page(sge);
+ from = sg_virt(sge);
+ to = page_address(page);
+ memcpy(to, from, a);
+ memcpy(to + a, from + a + pop, b);
+ sg_set_page(sge, page, a + b, 0);
+ put_page(orig);
+ }
+ pop = 0;
+ } else if (pop >= sge->length - a) {
+ sge->length = a;
+ pop -= (sge->length - a);
+ }
+ }
+
+ /* From above the current layout _must_ be as follows,
+ *
+ * -| offset
+ * -| start
+ *
+ * |---- pop ---|---------------- b ------------|
+ * |____________________________________________| length
+ *
+ * Offset and start of the current msg elem are equal because in the
+ * previous case we handled offset != start and either consumed the
+ * entire element and advanced to the next element OR pop == 0.
+ *
+ * Two cases to handle here are first pop is less than the length
+ * leaving some remainder b above. Simply adjust the element's layout
+ * in this case. Or pop >= length of the element so that b = 0. In this
+ * case advance to next element decrementing pop.
+ */
+ while (pop) {
+ struct scatterlist *sge = sk_msg_elem(msg, i);
+
+ if (pop < sge->length) {
+ sge->length -= pop;
+ sge->offset += pop;
+ pop = 0;
+ } else {
+ pop -= sge->length;
+ sk_msg_shift_left(msg, i);
+ }
+ sk_msg_iter_var_next(i);
+ }
+
+ sk_mem_uncharge(msg->sk, len - pop);
+ msg->sg.size -= (len - pop);
+ sk_msg_compute_data_pointers(msg);
+ return 0;
+}
+
+static const struct bpf_func_proto bpf_msg_pop_data_proto = {
+ .func = bpf_msg_pop_data,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_ANYTHING,
+ .arg3_type = ARG_ANYTHING,
+ .arg4_type = ARG_ANYTHING,
+};
+
BPF_CALL_1(bpf_get_cgroup_classid, const struct sk_buff *, skb)
{
return task_get_classid(skb);
@@ -3908,6 +4073,26 @@ static const struct bpf_func_proto bpf_get_socket_uid_proto = {
.arg1_type = ARG_PTR_TO_CTX,
};
+BPF_CALL_5(bpf_sockopt_event_output, struct bpf_sock_ops_kern *, bpf_sock,
+ struct bpf_map *, map, u64, flags, void *, data, u64, size)
+{
+ if (unlikely(flags & ~(BPF_F_INDEX_MASK)))
+ return -EINVAL;
+
+ return bpf_event_output(map, flags, data, size, NULL, 0, NULL);
+}
+
+static const struct bpf_func_proto bpf_sockopt_event_output_proto = {
+ .func = bpf_sockopt_event_output,
+ .gpl_only = true,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_CONST_MAP_PTR,
+ .arg3_type = ARG_ANYTHING,
+ .arg4_type = ARG_PTR_TO_MEM,
+ .arg5_type = ARG_CONST_SIZE_OR_ZERO,
+};
+
BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock,
int, level, int, optname, char *, optval, int, optlen)
{
@@ -4825,37 +5010,31 @@ static const struct bpf_func_proto bpf_lwt_seg6_adjust_srh_proto = {
#ifdef CONFIG_INET
static struct sock *sk_lookup(struct net *net, struct bpf_sock_tuple *tuple,
- struct sk_buff *skb, u8 family, u8 proto)
+ int dif, int sdif, u8 family, u8 proto)
{
bool refcounted = false;
struct sock *sk = NULL;
- int dif = 0;
-
- if (skb->dev)
- dif = skb->dev->ifindex;
if (family == AF_INET) {
__be32 src4 = tuple->ipv4.saddr;
__be32 dst4 = tuple->ipv4.daddr;
- int sdif = inet_sdif(skb);
if (proto == IPPROTO_TCP)
- sk = __inet_lookup(net, &tcp_hashinfo, skb, 0,
+ sk = __inet_lookup(net, &tcp_hashinfo, NULL, 0,
src4, tuple->ipv4.sport,
dst4, tuple->ipv4.dport,
dif, sdif, &refcounted);
else
sk = __udp4_lib_lookup(net, src4, tuple->ipv4.sport,
dst4, tuple->ipv4.dport,
- dif, sdif, &udp_table, skb);
+ dif, sdif, &udp_table, NULL);
#if IS_ENABLED(CONFIG_IPV6)
} else {
struct in6_addr *src6 = (struct in6_addr *)&tuple->ipv6.saddr;
struct in6_addr *dst6 = (struct in6_addr *)&tuple->ipv6.daddr;
- int sdif = inet6_sdif(skb);
if (proto == IPPROTO_TCP)
- sk = __inet6_lookup(net, &tcp_hashinfo, skb, 0,
+ sk = __inet6_lookup(net, &tcp_hashinfo, NULL, 0,
src6, tuple->ipv6.sport,
dst6, ntohs(tuple->ipv6.dport),
dif, sdif, &refcounted);
@@ -4864,7 +5043,7 @@ static struct sock *sk_lookup(struct net *net, struct bpf_sock_tuple *tuple,
src6, tuple->ipv6.sport,
dst6, tuple->ipv6.dport,
dif, sdif,
- &udp_table, skb);
+ &udp_table, NULL);
#endif
}
@@ -4881,31 +5060,33 @@ static struct sock *sk_lookup(struct net *net, struct bpf_sock_tuple *tuple,
* callers to satisfy BPF_CALL declarations.
*/
static unsigned long
-bpf_sk_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len,
- u8 proto, u64 netns_id, u64 flags)
+__bpf_sk_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len,
+ struct net *caller_net, u32 ifindex, u8 proto, u64 netns_id,
+ u64 flags)
{
- struct net *caller_net;
struct sock *sk = NULL;
u8 family = AF_UNSPEC;
struct net *net;
+ int sdif;
family = len == sizeof(tuple->ipv4) ? AF_INET : AF_INET6;
if (unlikely(family == AF_UNSPEC || flags ||
!((s32)netns_id < 0 || netns_id <= S32_MAX)))
goto out;
- if (skb->dev)
- caller_net = dev_net(skb->dev);
+ if (family == AF_INET)
+ sdif = inet_sdif(skb);
else
- caller_net = sock_net(skb->sk);
+ sdif = inet6_sdif(skb);
+
if ((s32)netns_id < 0) {
net = caller_net;
- sk = sk_lookup(net, tuple, skb, family, proto);
+ sk = sk_lookup(net, tuple, ifindex, sdif, family, proto);
} else {
net = get_net_ns_by_id(caller_net, netns_id);
if (unlikely(!net))
goto out;
- sk = sk_lookup(net, tuple, skb, family, proto);
+ sk = sk_lookup(net, tuple, ifindex, sdif, family, proto);
put_net(net);
}
@@ -4915,6 +5096,25 @@ out:
return (unsigned long) sk;
}
+static unsigned long
+bpf_sk_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len,
+ u8 proto, u64 netns_id, u64 flags)
+{
+ struct net *caller_net;
+ int ifindex;
+
+ if (skb->dev) {
+ caller_net = dev_net(skb->dev);
+ ifindex = skb->dev->ifindex;
+ } else {
+ caller_net = sock_net(skb->sk);
+ ifindex = 0;
+ }
+
+ return __bpf_sk_lookup(skb, tuple, len, caller_net, ifindex,
+ proto, netns_id, flags);
+}
+
BPF_CALL_5(bpf_sk_lookup_tcp, struct sk_buff *, skb,
struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags)
{
@@ -4964,6 +5164,87 @@ static const struct bpf_func_proto bpf_sk_release_proto = {
.ret_type = RET_INTEGER,
.arg1_type = ARG_PTR_TO_SOCKET,
};
+
+BPF_CALL_5(bpf_xdp_sk_lookup_udp, struct xdp_buff *, ctx,
+ struct bpf_sock_tuple *, tuple, u32, len, u32, netns_id, u64, flags)
+{
+ struct net *caller_net = dev_net(ctx->rxq->dev);
+ int ifindex = ctx->rxq->dev->ifindex;
+
+ return __bpf_sk_lookup(NULL, tuple, len, caller_net, ifindex,
+ IPPROTO_UDP, netns_id, flags);
+}
+
+static const struct bpf_func_proto bpf_xdp_sk_lookup_udp_proto = {
+ .func = bpf_xdp_sk_lookup_udp,
+ .gpl_only = false,
+ .pkt_access = true,
+ .ret_type = RET_PTR_TO_SOCKET_OR_NULL,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_PTR_TO_MEM,
+ .arg3_type = ARG_CONST_SIZE,
+ .arg4_type = ARG_ANYTHING,
+ .arg5_type = ARG_ANYTHING,
+};
+
+BPF_CALL_5(bpf_xdp_sk_lookup_tcp, struct xdp_buff *, ctx,
+ struct bpf_sock_tuple *, tuple, u32, len, u32, netns_id, u64, flags)
+{
+ struct net *caller_net = dev_net(ctx->rxq->dev);
+ int ifindex = ctx->rxq->dev->ifindex;
+
+ return __bpf_sk_lookup(NULL, tuple, len, caller_net, ifindex,
+ IPPROTO_TCP, netns_id, flags);
+}
+
+static const struct bpf_func_proto bpf_xdp_sk_lookup_tcp_proto = {
+ .func = bpf_xdp_sk_lookup_tcp,
+ .gpl_only = false,
+ .pkt_access = true,
+ .ret_type = RET_PTR_TO_SOCKET_OR_NULL,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_PTR_TO_MEM,
+ .arg3_type = ARG_CONST_SIZE,
+ .arg4_type = ARG_ANYTHING,
+ .arg5_type = ARG_ANYTHING,
+};
+
+BPF_CALL_5(bpf_sock_addr_sk_lookup_tcp, struct bpf_sock_addr_kern *, ctx,
+ struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags)
+{
+ return __bpf_sk_lookup(NULL, tuple, len, sock_net(ctx->sk), 0,
+ IPPROTO_TCP, netns_id, flags);
+}
+
+static const struct bpf_func_proto bpf_sock_addr_sk_lookup_tcp_proto = {
+ .func = bpf_sock_addr_sk_lookup_tcp,
+ .gpl_only = false,
+ .ret_type = RET_PTR_TO_SOCKET_OR_NULL,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_PTR_TO_MEM,
+ .arg3_type = ARG_CONST_SIZE,
+ .arg4_type = ARG_ANYTHING,
+ .arg5_type = ARG_ANYTHING,
+};
+
+BPF_CALL_5(bpf_sock_addr_sk_lookup_udp, struct bpf_sock_addr_kern *, ctx,
+ struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags)
+{
+ return __bpf_sk_lookup(NULL, tuple, len, sock_net(ctx->sk), 0,
+ IPPROTO_UDP, netns_id, flags);
+}
+
+static const struct bpf_func_proto bpf_sock_addr_sk_lookup_udp_proto = {
+ .func = bpf_sock_addr_sk_lookup_udp,
+ .gpl_only = false,
+ .ret_type = RET_PTR_TO_SOCKET_OR_NULL,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_PTR_TO_MEM,
+ .arg3_type = ARG_CONST_SIZE,
+ .arg4_type = ARG_ANYTHING,
+ .arg5_type = ARG_ANYTHING,
+};
+
#endif /* CONFIG_INET */
bool bpf_helper_changes_pkt_data(void *func)
@@ -4986,6 +5267,7 @@ bool bpf_helper_changes_pkt_data(void *func)
func == bpf_xdp_adjust_meta ||
func == bpf_msg_pull_data ||
func == bpf_msg_push_data ||
+ func == bpf_msg_pop_data ||
func == bpf_xdp_adjust_tail ||
#if IS_ENABLED(CONFIG_IPV6_SEG6_BPF)
func == bpf_lwt_seg6_store_bytes ||
@@ -5070,6 +5352,14 @@ sock_addr_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
return &bpf_get_socket_cookie_sock_addr_proto;
case BPF_FUNC_get_local_storage:
return &bpf_get_local_storage_proto;
+#ifdef CONFIG_INET
+ case BPF_FUNC_sk_lookup_tcp:
+ return &bpf_sock_addr_sk_lookup_tcp_proto;
+ case BPF_FUNC_sk_lookup_udp:
+ return &bpf_sock_addr_sk_lookup_udp_proto;
+ case BPF_FUNC_sk_release:
+ return &bpf_sk_release_proto;
+#endif /* CONFIG_INET */
default:
return bpf_base_func_proto(func_id);
}
@@ -5214,6 +5504,14 @@ xdp_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
return &bpf_xdp_adjust_tail_proto;
case BPF_FUNC_fib_lookup:
return &bpf_xdp_fib_lookup_proto;
+#ifdef CONFIG_INET
+ case BPF_FUNC_sk_lookup_udp:
+ return &bpf_xdp_sk_lookup_udp_proto;
+ case BPF_FUNC_sk_lookup_tcp:
+ return &bpf_xdp_sk_lookup_tcp_proto;
+ case BPF_FUNC_sk_release:
+ return &bpf_sk_release_proto;
+#endif
default:
return bpf_base_func_proto(func_id);
}
@@ -5240,6 +5538,8 @@ sock_ops_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
return &bpf_get_socket_cookie_sock_ops_proto;
case BPF_FUNC_get_local_storage:
return &bpf_get_local_storage_proto;
+ case BPF_FUNC_perf_event_output:
+ return &bpf_sockopt_event_output_proto;
default:
return bpf_base_func_proto(func_id);
}
@@ -5264,6 +5564,8 @@ sk_msg_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
return &bpf_msg_pull_data_proto;
case BPF_FUNC_msg_push_data:
return &bpf_msg_push_data_proto;
+ case BPF_FUNC_msg_pop_data:
+ return &bpf_msg_pop_data_proto;
default:
return bpf_base_func_proto(func_id);
}
@@ -5440,6 +5742,10 @@ static bool bpf_skb_is_valid_access(int off, int size, enum bpf_access_type type
if (size != sizeof(__u64))
return false;
break;
+ case bpf_ctx_range(struct __sk_buff, tstamp):
+ if (size != sizeof(__u64))
+ return false;
+ break;
default:
/* Only narrow read access allowed for now. */
if (type == BPF_WRITE) {
@@ -5467,6 +5773,8 @@ static bool sk_filter_is_valid_access(int off, int size,
case bpf_ctx_range(struct __sk_buff, data_end):
case bpf_ctx_range_ptr(struct __sk_buff, flow_keys):
case bpf_ctx_range_till(struct __sk_buff, family, local_port):
+ case bpf_ctx_range(struct __sk_buff, tstamp):
+ case bpf_ctx_range(struct __sk_buff, wire_len):
return false;
}
@@ -5491,6 +5799,7 @@ static bool cg_skb_is_valid_access(int off, int size,
case bpf_ctx_range(struct __sk_buff, tc_classid):
case bpf_ctx_range(struct __sk_buff, data_meta):
case bpf_ctx_range_ptr(struct __sk_buff, flow_keys):
+ case bpf_ctx_range(struct __sk_buff, wire_len):
return false;
case bpf_ctx_range(struct __sk_buff, data):
case bpf_ctx_range(struct __sk_buff, data_end):
@@ -5505,6 +5814,10 @@ static bool cg_skb_is_valid_access(int off, int size,
case bpf_ctx_range(struct __sk_buff, priority):
case bpf_ctx_range_till(struct __sk_buff, cb[0], cb[4]):
break;
+ case bpf_ctx_range(struct __sk_buff, tstamp):
+ if (!capable(CAP_SYS_ADMIN))
+ return false;
+ break;
default:
return false;
}
@@ -5532,6 +5845,8 @@ static bool lwt_is_valid_access(int off, int size,
case bpf_ctx_range_till(struct __sk_buff, family, local_port):
case bpf_ctx_range(struct __sk_buff, data_meta):
case bpf_ctx_range_ptr(struct __sk_buff, flow_keys):
+ case bpf_ctx_range(struct __sk_buff, tstamp):
+ case bpf_ctx_range(struct __sk_buff, wire_len):
return false;
}
@@ -5741,6 +6056,7 @@ static bool tc_cls_act_is_valid_access(int off, int size,
case bpf_ctx_range(struct __sk_buff, priority):
case bpf_ctx_range(struct __sk_buff, tc_classid):
case bpf_ctx_range_till(struct __sk_buff, cb[0], cb[4]):
+ case bpf_ctx_range(struct __sk_buff, tstamp):
break;
default:
return false;
@@ -5960,6 +6276,8 @@ static bool sk_skb_is_valid_access(int off, int size,
case bpf_ctx_range(struct __sk_buff, tc_classid):
case bpf_ctx_range(struct __sk_buff, data_meta):
case bpf_ctx_range_ptr(struct __sk_buff, flow_keys):
+ case bpf_ctx_range(struct __sk_buff, tstamp):
+ case bpf_ctx_range(struct __sk_buff, wire_len):
return false;
}
@@ -5995,6 +6313,9 @@ static bool sk_msg_is_valid_access(int off, int size,
if (type == BPF_WRITE)
return false;
+ if (off % size != 0)
+ return false;
+
switch (off) {
case offsetof(struct sk_msg_md, data):
info->reg_type = PTR_TO_PACKET;
@@ -6006,16 +6327,20 @@ static bool sk_msg_is_valid_access(int off, int size,
if (size != sizeof(__u64))
return false;
break;
- default:
+ case bpf_ctx_range(struct sk_msg_md, family):
+ case bpf_ctx_range(struct sk_msg_md, remote_ip4):
+ case bpf_ctx_range(struct sk_msg_md, local_ip4):
+ case bpf_ctx_range_till(struct sk_msg_md, remote_ip6[0], remote_ip6[3]):
+ case bpf_ctx_range_till(struct sk_msg_md, local_ip6[0], local_ip6[3]):
+ case bpf_ctx_range(struct sk_msg_md, remote_port):
+ case bpf_ctx_range(struct sk_msg_md, local_port):
+ case bpf_ctx_range(struct sk_msg_md, size):
if (size != sizeof(__u32))
return false;
- }
-
- if (off < 0 || off >= sizeof(struct sk_msg_md))
- return false;
- if (off % size != 0)
+ break;
+ default:
return false;
-
+ }
return true;
}
@@ -6046,6 +6371,8 @@ static bool flow_dissector_is_valid_access(int off, int size,
case bpf_ctx_range(struct __sk_buff, tc_classid):
case bpf_ctx_range(struct __sk_buff, data_meta):
case bpf_ctx_range_till(struct __sk_buff, family, local_port):
+ case bpf_ctx_range(struct __sk_buff, tstamp):
+ case bpf_ctx_range(struct __sk_buff, wire_len):
return false;
}
@@ -6140,19 +6467,19 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type,
break;
case offsetof(struct __sk_buff, vlan_present):
- case offsetof(struct __sk_buff, vlan_tci):
- BUILD_BUG_ON(VLAN_TAG_PRESENT != 0x1000);
+ *target_size = 1;
+ *insn++ = BPF_LDX_MEM(BPF_B, si->dst_reg, si->src_reg,
+ PKT_VLAN_PRESENT_OFFSET());
+ if (PKT_VLAN_PRESENT_BIT)
+ *insn++ = BPF_ALU32_IMM(BPF_RSH, si->dst_reg, PKT_VLAN_PRESENT_BIT);
+ if (PKT_VLAN_PRESENT_BIT < 7)
+ *insn++ = BPF_ALU32_IMM(BPF_AND, si->dst_reg, 1);
+ break;
+ case offsetof(struct __sk_buff, vlan_tci):
*insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->src_reg,
bpf_target_off(struct sk_buff, vlan_tci, 2,
target_size));
- if (si->off == offsetof(struct __sk_buff, vlan_tci)) {
- *insn++ = BPF_ALU32_IMM(BPF_AND, si->dst_reg,
- ~VLAN_TAG_PRESENT);
- } else {
- *insn++ = BPF_ALU32_IMM(BPF_RSH, si->dst_reg, 12);
- *insn++ = BPF_ALU32_IMM(BPF_AND, si->dst_reg, 1);
- }
break;
case offsetof(struct __sk_buff, cb[0]) ...
@@ -6355,6 +6682,33 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type,
*insn++ = BPF_LDX_MEM(BPF_SIZEOF(void *), si->dst_reg,
si->src_reg, off);
break;
+
+ case offsetof(struct __sk_buff, tstamp):
+ BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, tstamp) != 8);
+
+ if (type == BPF_WRITE)
+ *insn++ = BPF_STX_MEM(BPF_DW,
+ si->dst_reg, si->src_reg,
+ bpf_target_off(struct sk_buff,
+ tstamp, 8,
+ target_size));
+ else
+ *insn++ = BPF_LDX_MEM(BPF_DW,
+ si->dst_reg, si->src_reg,
+ bpf_target_off(struct sk_buff,
+ tstamp, 8,
+ target_size));
+ break;
+
+ case offsetof(struct __sk_buff, wire_len):
+ BUILD_BUG_ON(FIELD_SIZEOF(struct qdisc_skb_cb, pkt_len) != 4);
+
+ off = si->off;
+ off -= offsetof(struct __sk_buff, wire_len);
+ off += offsetof(struct sk_buff, cb);
+ off += offsetof(struct qdisc_skb_cb, pkt_len);
+ *target_size = 4;
+ *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, off);
}
return insn - insn_buf;
@@ -7071,6 +7425,9 @@ static u32 sk_msg_convert_ctx_access(enum bpf_access_type type,
int off;
#endif
+ /* convert ctx uses the fact sg element is first in struct */
+ BUILD_BUG_ON(offsetof(struct sk_msg, sg) != 0);
+
switch (si->off) {
case offsetof(struct sk_msg_md, data):
*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_msg, data),
@@ -7183,6 +7540,12 @@ static u32 sk_msg_convert_ctx_access(enum bpf_access_type type,
*insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->dst_reg,
offsetof(struct sock_common, skc_num));
break;
+
+ case offsetof(struct sk_msg_md, size):
+ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_msg_sg, size),
+ si->dst_reg, si->src_reg,
+ offsetof(struct sk_msg_sg, size));
+ break;
}
return insn - insn_buf;
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index af68207ee56c..9f2840510e63 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -956,8 +956,7 @@ proto_again:
if (!vlan) {
key_vlan->vlan_id = skb_vlan_tag_get_id(skb);
- key_vlan->vlan_priority =
- (skb_vlan_tag_get_prio(skb) >> VLAN_PRIO_SHIFT);
+ key_vlan->vlan_priority = skb_vlan_tag_get_prio(skb);
} else {
key_vlan->vlan_id = ntohs(vlan->h_vlan_TCI) &
VLAN_VID_MASK;
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 5fa32c064baf..763a7b08df67 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -118,21 +118,77 @@ unsigned long neigh_rand_reach_time(unsigned long base)
}
EXPORT_SYMBOL(neigh_rand_reach_time);
+static void neigh_mark_dead(struct neighbour *n)
+{
+ n->dead = 1;
+ if (!list_empty(&n->gc_list)) {
+ list_del_init(&n->gc_list);
+ atomic_dec(&n->tbl->gc_entries);
+ }
+}
+
+static void neigh_update_gc_list(struct neighbour *n)
+{
+ bool on_gc_list, exempt_from_gc;
+
+ write_lock_bh(&n->tbl->lock);
+ write_lock(&n->lock);
+
+ /* remove from the gc list if new state is permanent or if neighbor
+ * is externally learned; otherwise entry should be on the gc list
+ */
+ exempt_from_gc = n->nud_state & NUD_PERMANENT ||
+ n->flags & NTF_EXT_LEARNED;
+ on_gc_list = !list_empty(&n->gc_list);
+
+ if (exempt_from_gc && on_gc_list) {
+ list_del_init(&n->gc_list);
+ atomic_dec(&n->tbl->gc_entries);
+ } else if (!exempt_from_gc && !on_gc_list) {
+ /* add entries to the tail; cleaning removes from the front */
+ list_add_tail(&n->gc_list, &n->tbl->gc_list);
+ atomic_inc(&n->tbl->gc_entries);
+ }
+
+ write_unlock(&n->lock);
+ write_unlock_bh(&n->tbl->lock);
+}
-static bool neigh_del(struct neighbour *n, __u8 state, __u8 flags,
- struct neighbour __rcu **np, struct neigh_table *tbl)
+static bool neigh_update_ext_learned(struct neighbour *neigh, u32 flags,
+ int *notify)
+{
+ bool rc = false;
+ u8 ndm_flags;
+
+ if (!(flags & NEIGH_UPDATE_F_ADMIN))
+ return rc;
+
+ ndm_flags = (flags & NEIGH_UPDATE_F_EXT_LEARNED) ? NTF_EXT_LEARNED : 0;
+ if ((neigh->flags ^ ndm_flags) & NTF_EXT_LEARNED) {
+ if (ndm_flags & NTF_EXT_LEARNED)
+ neigh->flags |= NTF_EXT_LEARNED;
+ else
+ neigh->flags &= ~NTF_EXT_LEARNED;
+ rc = true;
+ *notify = 1;
+ }
+
+ return rc;
+}
+
+static bool neigh_del(struct neighbour *n, struct neighbour __rcu **np,
+ struct neigh_table *tbl)
{
bool retval = false;
write_lock(&n->lock);
- if (refcount_read(&n->refcnt) == 1 && !(n->nud_state & state) &&
- !(n->flags & flags)) {
+ if (refcount_read(&n->refcnt) == 1) {
struct neighbour *neigh;
neigh = rcu_dereference_protected(n->next,
lockdep_is_held(&tbl->lock));
rcu_assign_pointer(*np, neigh);
- n->dead = 1;
+ neigh_mark_dead(n);
retval = true;
}
write_unlock(&n->lock);
@@ -158,7 +214,7 @@ bool neigh_remove_one(struct neighbour *ndel, struct neigh_table *tbl)
while ((n = rcu_dereference_protected(*np,
lockdep_is_held(&tbl->lock)))) {
if (n == ndel)
- return neigh_del(n, 0, 0, np, tbl);
+ return neigh_del(n, np, tbl);
np = &n->next;
}
return false;
@@ -166,32 +222,29 @@ bool neigh_remove_one(struct neighbour *ndel, struct neigh_table *tbl)
static int neigh_forced_gc(struct neigh_table *tbl)
{
+ int max_clean = atomic_read(&tbl->gc_entries) - tbl->gc_thresh2;
+ unsigned long tref = jiffies - 5 * HZ;
+ struct neighbour *n, *tmp;
int shrunk = 0;
- int i;
- struct neigh_hash_table *nht;
NEIGH_CACHE_STAT_INC(tbl, forced_gc_runs);
write_lock_bh(&tbl->lock);
- nht = rcu_dereference_protected(tbl->nht,
- lockdep_is_held(&tbl->lock));
- for (i = 0; i < (1 << nht->hash_shift); i++) {
- struct neighbour *n;
- struct neighbour __rcu **np;
- np = &nht->hash_buckets[i];
- while ((n = rcu_dereference_protected(*np,
- lockdep_is_held(&tbl->lock))) != NULL) {
- /* Neighbour record may be discarded if:
- * - nobody refers to it.
- * - it is not permanent
- */
- if (neigh_del(n, NUD_PERMANENT, NTF_EXT_LEARNED, np,
- tbl)) {
- shrunk = 1;
- continue;
- }
- np = &n->next;
+ list_for_each_entry_safe(n, tmp, &tbl->gc_list, gc_list) {
+ if (refcount_read(&n->refcnt) == 1) {
+ bool remove = false;
+
+ write_lock(&n->lock);
+ if ((n->nud_state == NUD_FAILED) ||
+ time_after(tref, n->updated))
+ remove = true;
+ write_unlock(&n->lock);
+
+ if (remove && neigh_remove_one(n, tbl))
+ shrunk++;
+ if (shrunk >= max_clean)
+ break;
}
}
@@ -260,8 +313,7 @@ static void neigh_flush_dev(struct neigh_table *tbl, struct net_device *dev,
lockdep_is_held(&tbl->lock)));
write_lock(&n->lock);
neigh_del_timer(n);
- n->dead = 1;
-
+ neigh_mark_dead(n);
if (refcount_read(&n->refcnt) != 1) {
/* The most unpleasant situation.
We must destroy neighbour entry,
@@ -321,13 +373,18 @@ int neigh_ifdown(struct neigh_table *tbl, struct net_device *dev)
}
EXPORT_SYMBOL(neigh_ifdown);
-static struct neighbour *neigh_alloc(struct neigh_table *tbl, struct net_device *dev)
+static struct neighbour *neigh_alloc(struct neigh_table *tbl,
+ struct net_device *dev,
+ bool exempt_from_gc)
{
struct neighbour *n = NULL;
unsigned long now = jiffies;
int entries;
- entries = atomic_inc_return(&tbl->entries) - 1;
+ if (exempt_from_gc)
+ goto do_alloc;
+
+ entries = atomic_inc_return(&tbl->gc_entries) - 1;
if (entries >= tbl->gc_thresh3 ||
(entries >= tbl->gc_thresh2 &&
time_after(now, tbl->last_flush + 5 * HZ))) {
@@ -340,6 +397,7 @@ static struct neighbour *neigh_alloc(struct neigh_table *tbl, struct net_device
}
}
+do_alloc:
n = kzalloc(tbl->entry_size + dev->neigh_priv_len, GFP_ATOMIC);
if (!n)
goto out_entries;
@@ -358,11 +416,15 @@ static struct neighbour *neigh_alloc(struct neigh_table *tbl, struct net_device
n->tbl = tbl;
refcount_set(&n->refcnt, 1);
n->dead = 1;
+ INIT_LIST_HEAD(&n->gc_list);
+
+ atomic_inc(&tbl->entries);
out:
return n;
out_entries:
- atomic_dec(&tbl->entries);
+ if (!exempt_from_gc)
+ atomic_dec(&tbl->gc_entries);
goto out;
}
@@ -505,13 +567,15 @@ struct neighbour *neigh_lookup_nodev(struct neigh_table *tbl, struct net *net,
}
EXPORT_SYMBOL(neigh_lookup_nodev);
-struct neighbour *__neigh_create(struct neigh_table *tbl, const void *pkey,
- struct net_device *dev, bool want_ref)
+static struct neighbour *___neigh_create(struct neigh_table *tbl,
+ const void *pkey,
+ struct net_device *dev,
+ bool exempt_from_gc, bool want_ref)
{
+ struct neighbour *n1, *rc, *n = neigh_alloc(tbl, dev, exempt_from_gc);
u32 hash_val;
unsigned int key_len = tbl->key_len;
int error;
- struct neighbour *n1, *rc, *n = neigh_alloc(tbl, dev);
struct neigh_hash_table *nht;
if (!n) {
@@ -574,6 +638,9 @@ struct neighbour *__neigh_create(struct neigh_table *tbl, const void *pkey,
}
n->dead = 0;
+ if (!exempt_from_gc)
+ list_add_tail(&n->gc_list, &n->tbl->gc_list);
+
if (want_ref)
neigh_hold(n);
rcu_assign_pointer(n->next,
@@ -591,6 +658,12 @@ out_neigh_release:
neigh_release(n);
goto out;
}
+
+struct neighbour *__neigh_create(struct neigh_table *tbl, const void *pkey,
+ struct net_device *dev, bool want_ref)
+{
+ return ___neigh_create(tbl, pkey, dev, false, want_ref);
+}
EXPORT_SYMBOL(__neigh_create);
static u32 pneigh_hash(const void *pkey, unsigned int key_len)
@@ -652,6 +725,7 @@ struct pneigh_entry * pneigh_lookup(struct neigh_table *tbl,
if (!n)
goto out;
+ n->protocol = 0;
write_pnet(&n->net, net);
memcpy(n->key, pkey, key_len);
n->dev = dev;
@@ -854,7 +928,7 @@ static void neigh_periodic_work(struct work_struct *work)
(state == NUD_FAILED ||
time_after(jiffies, n->used + NEIGH_VAR(n->parms, GC_STALETIME)))) {
*np = n->next;
- n->dead = 1;
+ neigh_mark_dead(n);
write_unlock(&n->lock);
neigh_cleanup_and_release(n);
continue;
@@ -1137,9 +1211,11 @@ static void neigh_update_hhs(struct neighbour *neigh)
Caller MUST hold reference count on the entry.
*/
-int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new,
- u32 flags, u32 nlmsg_pid)
+static int __neigh_update(struct neighbour *neigh, const u8 *lladdr,
+ u8 new, u32 flags, u32 nlmsg_pid,
+ struct netlink_ext_ack *extack)
{
+ bool ext_learn_change = false;
u8 old;
int err;
int notify = 0;
@@ -1155,10 +1231,12 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new,
if (!(flags & NEIGH_UPDATE_F_ADMIN) &&
(old & (NUD_NOARP | NUD_PERMANENT)))
goto out;
- if (neigh->dead)
+ if (neigh->dead) {
+ NL_SET_ERR_MSG(extack, "Neighbor entry is now dead");
goto out;
+ }
- neigh_update_ext_learned(neigh, flags, &notify);
+ ext_learn_change = neigh_update_ext_learned(neigh, flags, &notify);
if (!(new & NUD_VALID)) {
neigh_del_timer(neigh);
@@ -1193,8 +1271,10 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new,
use it, otherwise discard the request.
*/
err = -EINVAL;
- if (!(old & NUD_VALID))
+ if (!(old & NUD_VALID)) {
+ NL_SET_ERR_MSG(extack, "No link layer address given");
goto out;
+ }
lladdr = neigh->ha;
}
@@ -1302,11 +1382,20 @@ out:
neigh_update_is_router(neigh, flags, &notify);
write_unlock_bh(&neigh->lock);
+ if (((new ^ old) & NUD_PERMANENT) || ext_learn_change)
+ neigh_update_gc_list(neigh);
+
if (notify)
neigh_update_notify(neigh, nlmsg_pid);
return err;
}
+
+int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new,
+ u32 flags, u32 nlmsg_pid)
+{
+ return __neigh_update(neigh, lladdr, new, flags, nlmsg_pid, NULL);
+}
EXPORT_SYMBOL(neigh_update);
/* Update the neigh to listen temporarily for probe responses, even if it is
@@ -1571,6 +1660,7 @@ void neigh_table_init(int index, struct neigh_table *tbl)
unsigned long phsize;
INIT_LIST_HEAD(&tbl->parms_list);
+ INIT_LIST_HEAD(&tbl->gc_list);
list_add(&tbl->parms.list, &tbl->parms_list);
write_pnet(&tbl->parms.net, &init_net);
refcount_set(&tbl->parms.refcnt, 1);
@@ -1662,6 +1752,19 @@ static struct neigh_table *neigh_find_table(int family)
return tbl;
}
+const struct nla_policy nda_policy[NDA_MAX+1] = {
+ [NDA_DST] = { .type = NLA_BINARY, .len = MAX_ADDR_LEN },
+ [NDA_LLADDR] = { .type = NLA_BINARY, .len = MAX_ADDR_LEN },
+ [NDA_CACHEINFO] = { .len = sizeof(struct nda_cacheinfo) },
+ [NDA_PROBES] = { .type = NLA_U32 },
+ [NDA_VLAN] = { .type = NLA_U16 },
+ [NDA_PORT] = { .type = NLA_U16 },
+ [NDA_VNI] = { .type = NLA_U32 },
+ [NDA_IFINDEX] = { .type = NLA_U32 },
+ [NDA_MASTER] = { .type = NLA_U32 },
+ [NDA_PROTOCOL] = { .type = NLA_U8 },
+};
+
static int neigh_delete(struct sk_buff *skb, struct nlmsghdr *nlh,
struct netlink_ext_ack *extack)
{
@@ -1678,8 +1781,10 @@ static int neigh_delete(struct sk_buff *skb, struct nlmsghdr *nlh,
goto out;
dst_attr = nlmsg_find_attr(nlh, sizeof(*ndm), NDA_DST);
- if (dst_attr == NULL)
+ if (!dst_attr) {
+ NL_SET_ERR_MSG(extack, "Network address not specified");
goto out;
+ }
ndm = nlmsg_data(nlh);
if (ndm->ndm_ifindex) {
@@ -1694,8 +1799,10 @@ static int neigh_delete(struct sk_buff *skb, struct nlmsghdr *nlh,
if (tbl == NULL)
return -EAFNOSUPPORT;
- if (nla_len(dst_attr) < (int)tbl->key_len)
+ if (nla_len(dst_attr) < (int)tbl->key_len) {
+ NL_SET_ERR_MSG(extack, "Invalid network address");
goto out;
+ }
if (ndm->ndm_flags & NTF_PROXY) {
err = pneigh_delete(tbl, net, nla_data(dst_attr), dev);
@@ -1711,10 +1818,9 @@ static int neigh_delete(struct sk_buff *skb, struct nlmsghdr *nlh,
goto out;
}
- err = neigh_update(neigh, NULL, NUD_FAILED,
- NEIGH_UPDATE_F_OVERRIDE |
- NEIGH_UPDATE_F_ADMIN,
- NETLINK_CB(skb).portid);
+ err = __neigh_update(neigh, NULL, NUD_FAILED,
+ NEIGH_UPDATE_F_OVERRIDE | NEIGH_UPDATE_F_ADMIN,
+ NETLINK_CB(skb).portid, extack);
write_lock_bh(&tbl->lock);
neigh_release(neigh);
neigh_remove_one(neigh, tbl);
@@ -1736,16 +1842,19 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh,
struct net_device *dev = NULL;
struct neighbour *neigh;
void *dst, *lladdr;
+ u8 protocol = 0;
int err;
ASSERT_RTNL();
- err = nlmsg_parse(nlh, sizeof(*ndm), tb, NDA_MAX, NULL, extack);
+ err = nlmsg_parse(nlh, sizeof(*ndm), tb, NDA_MAX, nda_policy, extack);
if (err < 0)
goto out;
err = -EINVAL;
- if (tb[NDA_DST] == NULL)
+ if (!tb[NDA_DST]) {
+ NL_SET_ERR_MSG(extack, "Network address not specified");
goto out;
+ }
ndm = nlmsg_data(nlh);
if (ndm->ndm_ifindex) {
@@ -1755,19 +1864,27 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh,
goto out;
}
- if (tb[NDA_LLADDR] && nla_len(tb[NDA_LLADDR]) < dev->addr_len)
+ if (tb[NDA_LLADDR] && nla_len(tb[NDA_LLADDR]) < dev->addr_len) {
+ NL_SET_ERR_MSG(extack, "Invalid link address");
goto out;
+ }
}
tbl = neigh_find_table(ndm->ndm_family);
if (tbl == NULL)
return -EAFNOSUPPORT;
- if (nla_len(tb[NDA_DST]) < (int)tbl->key_len)
+ if (nla_len(tb[NDA_DST]) < (int)tbl->key_len) {
+ NL_SET_ERR_MSG(extack, "Invalid network address");
goto out;
+ }
+
dst = nla_data(tb[NDA_DST]);
lladdr = tb[NDA_LLADDR] ? nla_data(tb[NDA_LLADDR]) : NULL;
+ if (tb[NDA_PROTOCOL])
+ protocol = nla_get_u8(tb[NDA_PROTOCOL]);
+
if (ndm->ndm_flags & NTF_PROXY) {
struct pneigh_entry *pn;
@@ -1775,22 +1892,30 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh,
pn = pneigh_lookup(tbl, net, dst, dev, 1);
if (pn) {
pn->flags = ndm->ndm_flags;
+ if (protocol)
+ pn->protocol = protocol;
err = 0;
}
goto out;
}
- if (dev == NULL)
+ if (!dev) {
+ NL_SET_ERR_MSG(extack, "Device not specified");
goto out;
+ }
neigh = neigh_lookup(tbl, dst, dev);
if (neigh == NULL) {
+ bool exempt_from_gc;
+
if (!(nlh->nlmsg_flags & NLM_F_CREATE)) {
err = -ENOENT;
goto out;
}
- neigh = __neigh_lookup_errno(tbl, dst, dev);
+ exempt_from_gc = ndm->ndm_state & NUD_PERMANENT ||
+ ndm->ndm_flags & NTF_EXT_LEARNED;
+ neigh = ___neigh_create(tbl, dst, dev, exempt_from_gc, true);
if (IS_ERR(neigh)) {
err = PTR_ERR(neigh);
goto out;
@@ -1817,8 +1942,12 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh,
neigh_event_send(neigh, NULL);
err = 0;
} else
- err = neigh_update(neigh, lladdr, ndm->ndm_state, flags,
- NETLINK_CB(skb).portid);
+ err = __neigh_update(neigh, lladdr, ndm->ndm_state, flags,
+ NETLINK_CB(skb).portid, extack);
+
+ if (protocol)
+ neigh->protocol = protocol;
+
neigh_release(neigh);
out:
@@ -2312,6 +2441,9 @@ static int neigh_fill_info(struct sk_buff *skb, struct neighbour *neigh,
nla_put(skb, NDA_CACHEINFO, sizeof(ci), &ci))
goto nla_put_failure;
+ if (neigh->protocol && nla_put_u8(skb, NDA_PROTOCOL, neigh->protocol))
+ goto nla_put_failure;
+
nlmsg_end(skb, nlh);
return 0;
@@ -2343,6 +2475,9 @@ static int pneigh_fill_info(struct sk_buff *skb, struct pneigh_entry *pn,
if (nla_put(skb, NDA_DST, tbl->key_len, pn->key))
goto nla_put_failure;
+ if (pn->protocol && nla_put_u8(skb, NDA_PROTOCOL, pn->protocol))
+ goto nla_put_failure;
+
nlmsg_end(skb, nlh);
return 0;
@@ -2505,10 +2640,10 @@ static int neigh_valid_dump_req(const struct nlmsghdr *nlh,
}
err = nlmsg_parse_strict(nlh, sizeof(struct ndmsg), tb, NDA_MAX,
- NULL, extack);
+ nda_policy, extack);
} else {
err = nlmsg_parse(nlh, sizeof(struct ndmsg), tb, NDA_MAX,
- NULL, extack);
+ nda_policy, extack);
}
if (err < 0)
return err;
@@ -2520,17 +2655,9 @@ static int neigh_valid_dump_req(const struct nlmsghdr *nlh,
/* all new attributes should require strict_check */
switch (i) {
case NDA_IFINDEX:
- if (nla_len(tb[i]) != sizeof(u32)) {
- NL_SET_ERR_MSG(extack, "Invalid IFINDEX attribute in neighbor dump request");
- return -EINVAL;
- }
filter->dev_idx = nla_get_u32(tb[i]);
break;
case NDA_MASTER:
- if (nla_len(tb[i]) != sizeof(u32)) {
- NL_SET_ERR_MSG(extack, "Invalid MASTER attribute in neighbor dump request");
- return -EINVAL;
- }
filter->master_idx = nla_get_u32(tb[i]);
break;
default:
@@ -2590,6 +2717,186 @@ static int neigh_dump_info(struct sk_buff *skb, struct netlink_callback *cb)
return skb->len;
}
+static int neigh_valid_get_req(const struct nlmsghdr *nlh,
+ struct neigh_table **tbl,
+ void **dst, int *dev_idx, u8 *ndm_flags,
+ struct netlink_ext_ack *extack)
+{
+ struct nlattr *tb[NDA_MAX + 1];
+ struct ndmsg *ndm;
+ int err, i;
+
+ if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ndm))) {
+ NL_SET_ERR_MSG(extack, "Invalid header for neighbor get request");
+ return -EINVAL;
+ }
+
+ ndm = nlmsg_data(nlh);
+ if (ndm->ndm_pad1 || ndm->ndm_pad2 || ndm->ndm_state ||
+ ndm->ndm_type) {
+ NL_SET_ERR_MSG(extack, "Invalid values in header for neighbor get request");
+ return -EINVAL;
+ }
+
+ if (ndm->ndm_flags & ~NTF_PROXY) {
+ NL_SET_ERR_MSG(extack, "Invalid flags in header for neighbor get request");
+ return -EINVAL;
+ }
+
+ err = nlmsg_parse_strict(nlh, sizeof(struct ndmsg), tb, NDA_MAX,
+ nda_policy, extack);
+ if (err < 0)
+ return err;
+
+ *ndm_flags = ndm->ndm_flags;
+ *dev_idx = ndm->ndm_ifindex;
+ *tbl = neigh_find_table(ndm->ndm_family);
+ if (*tbl == NULL) {
+ NL_SET_ERR_MSG(extack, "Unsupported family in header for neighbor get request");
+ return -EAFNOSUPPORT;
+ }
+
+ for (i = 0; i <= NDA_MAX; ++i) {
+ if (!tb[i])
+ continue;
+
+ switch (i) {
+ case NDA_DST:
+ if (nla_len(tb[i]) != (int)(*tbl)->key_len) {
+ NL_SET_ERR_MSG(extack, "Invalid network address in neighbor get request");
+ return -EINVAL;
+ }
+ *dst = nla_data(tb[i]);
+ break;
+ default:
+ NL_SET_ERR_MSG(extack, "Unsupported attribute in neighbor get request");
+ return -EINVAL;
+ }
+ }
+
+ return 0;
+}
+
+static inline size_t neigh_nlmsg_size(void)
+{
+ return NLMSG_ALIGN(sizeof(struct ndmsg))
+ + nla_total_size(MAX_ADDR_LEN) /* NDA_DST */
+ + nla_total_size(MAX_ADDR_LEN) /* NDA_LLADDR */
+ + nla_total_size(sizeof(struct nda_cacheinfo))
+ + nla_total_size(4) /* NDA_PROBES */
+ + nla_total_size(1); /* NDA_PROTOCOL */
+}
+
+static int neigh_get_reply(struct net *net, struct neighbour *neigh,
+ u32 pid, u32 seq)
+{
+ struct sk_buff *skb;
+ int err = 0;
+
+ skb = nlmsg_new(neigh_nlmsg_size(), GFP_KERNEL);
+ if (!skb)
+ return -ENOBUFS;
+
+ err = neigh_fill_info(skb, neigh, pid, seq, RTM_NEWNEIGH, 0);
+ if (err) {
+ kfree_skb(skb);
+ goto errout;
+ }
+
+ err = rtnl_unicast(skb, net, pid);
+errout:
+ return err;
+}
+
+static inline size_t pneigh_nlmsg_size(void)
+{
+ return NLMSG_ALIGN(sizeof(struct ndmsg))
+ + nla_total_size(MAX_ADDR_LEN) /* NDA_DST */
+ + nla_total_size(1); /* NDA_PROTOCOL */
+}
+
+static int pneigh_get_reply(struct net *net, struct pneigh_entry *neigh,
+ u32 pid, u32 seq, struct neigh_table *tbl)
+{
+ struct sk_buff *skb;
+ int err = 0;
+
+ skb = nlmsg_new(pneigh_nlmsg_size(), GFP_KERNEL);
+ if (!skb)
+ return -ENOBUFS;
+
+ err = pneigh_fill_info(skb, neigh, pid, seq, RTM_NEWNEIGH, 0, tbl);
+ if (err) {
+ kfree_skb(skb);
+ goto errout;
+ }
+
+ err = rtnl_unicast(skb, net, pid);
+errout:
+ return err;
+}
+
+static int neigh_get(struct sk_buff *in_skb, struct nlmsghdr *nlh,
+ struct netlink_ext_ack *extack)
+{
+ struct net *net = sock_net(in_skb->sk);
+ struct net_device *dev = NULL;
+ struct neigh_table *tbl = NULL;
+ struct neighbour *neigh;
+ void *dst = NULL;
+ u8 ndm_flags = 0;
+ int dev_idx = 0;
+ int err;
+
+ err = neigh_valid_get_req(nlh, &tbl, &dst, &dev_idx, &ndm_flags,
+ extack);
+ if (err < 0)
+ return err;
+
+ if (dev_idx) {
+ dev = __dev_get_by_index(net, dev_idx);
+ if (!dev) {
+ NL_SET_ERR_MSG(extack, "Unknown device ifindex");
+ return -ENODEV;
+ }
+ }
+
+ if (!dst) {
+ NL_SET_ERR_MSG(extack, "Network address not specified");
+ return -EINVAL;
+ }
+
+ if (ndm_flags & NTF_PROXY) {
+ struct pneigh_entry *pn;
+
+ pn = pneigh_lookup(tbl, net, dst, dev, 0);
+ if (!pn) {
+ NL_SET_ERR_MSG(extack, "Proxy neighbour entry not found");
+ return -ENOENT;
+ }
+ return pneigh_get_reply(net, pn, NETLINK_CB(in_skb).portid,
+ nlh->nlmsg_seq, tbl);
+ }
+
+ if (!dev) {
+ NL_SET_ERR_MSG(extack, "No device specified");
+ return -EINVAL;
+ }
+
+ neigh = neigh_lookup(tbl, dst, dev);
+ if (!neigh) {
+ NL_SET_ERR_MSG(extack, "Neighbour entry not found");
+ return -ENOENT;
+ }
+
+ err = neigh_get_reply(net, neigh, NETLINK_CB(in_skb).portid,
+ nlh->nlmsg_seq);
+
+ neigh_release(neigh);
+
+ return err;
+}
+
void neigh_for_each(struct neigh_table *tbl, void (*cb)(struct neighbour *, void *), void *cookie)
{
int chain;
@@ -2636,7 +2943,7 @@ void __neigh_for_each_release(struct neigh_table *tbl,
rcu_assign_pointer(*np,
rcu_dereference_protected(n->next,
lockdep_is_held(&tbl->lock)));
- n->dead = 1;
+ neigh_mark_dead(n);
} else
np = &n->next;
write_unlock(&n->lock);
@@ -2997,15 +3304,6 @@ static const struct seq_operations neigh_stat_seq_ops = {
};
#endif /* CONFIG_PROC_FS */
-static inline size_t neigh_nlmsg_size(void)
-{
- return NLMSG_ALIGN(sizeof(struct ndmsg))
- + nla_total_size(MAX_ADDR_LEN) /* NDA_DST */
- + nla_total_size(MAX_ADDR_LEN) /* NDA_LLADDR */
- + nla_total_size(sizeof(struct nda_cacheinfo))
- + nla_total_size(4); /* NDA_PROBES */
-}
-
static void __neigh_notify(struct neighbour *n, int type, int flags,
u32 pid)
{
@@ -3389,7 +3687,7 @@ static int __init neigh_init(void)
{
rtnl_register(PF_UNSPEC, RTM_NEWNEIGH, neigh_add, NULL, 0);
rtnl_register(PF_UNSPEC, RTM_DELNEIGH, neigh_delete, NULL, 0);
- rtnl_register(PF_UNSPEC, RTM_GETNEIGH, NULL, neigh_dump_info, 0);
+ rtnl_register(PF_UNSPEC, RTM_GETNEIGH, neigh_get, neigh_dump_info, 0);
rtnl_register(PF_UNSPEC, RTM_GETNEIGHTBL, NULL, neightbl_dump_info,
0);
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index bd67c4d0fcfd..ff9fd2bb4ce4 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -337,7 +337,7 @@ NETDEVICE_SHOW_RW(mtu, fmt_dec);
static int change_flags(struct net_device *dev, unsigned long new_flags)
{
- return dev_change_flags(dev, (unsigned int)new_flags);
+ return dev_change_flags(dev, (unsigned int)new_flags, NULL);
}
static ssize_t flags_store(struct device *dev, struct device_attribute *attr,
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index fefe72774aeb..b02fb19df2cc 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -669,6 +669,7 @@ static const struct nla_policy rtnl_net_policy[NETNSA_MAX + 1] = {
[NETNSA_NSID] = { .type = NLA_S32 },
[NETNSA_PID] = { .type = NLA_U32 },
[NETNSA_FD] = { .type = NLA_U32 },
+ [NETNSA_TARGET_NSID] = { .type = NLA_S32 },
};
static int rtnl_net_newid(struct sk_buff *skb, struct nlmsghdr *nlh,
@@ -735,23 +736,38 @@ static int rtnl_net_get_size(void)
{
return NLMSG_ALIGN(sizeof(struct rtgenmsg))
+ nla_total_size(sizeof(s32)) /* NETNSA_NSID */
+ + nla_total_size(sizeof(s32)) /* NETNSA_CURRENT_NSID */
;
}
-static int rtnl_net_fill(struct sk_buff *skb, u32 portid, u32 seq, int flags,
- int cmd, struct net *net, int nsid)
+struct net_fill_args {
+ u32 portid;
+ u32 seq;
+ int flags;
+ int cmd;
+ int nsid;
+ bool add_ref;
+ int ref_nsid;
+};
+
+static int rtnl_net_fill(struct sk_buff *skb, struct net_fill_args *args)
{
struct nlmsghdr *nlh;
struct rtgenmsg *rth;
- nlh = nlmsg_put(skb, portid, seq, cmd, sizeof(*rth), flags);
+ nlh = nlmsg_put(skb, args->portid, args->seq, args->cmd, sizeof(*rth),
+ args->flags);
if (!nlh)
return -EMSGSIZE;
rth = nlmsg_data(nlh);
rth->rtgen_family = AF_UNSPEC;
- if (nla_put_s32(skb, NETNSA_NSID, nsid))
+ if (nla_put_s32(skb, NETNSA_NSID, args->nsid))
+ goto nla_put_failure;
+
+ if (args->add_ref &&
+ nla_put_s32(skb, NETNSA_CURRENT_NSID, args->ref_nsid))
goto nla_put_failure;
nlmsg_end(skb, nlh);
@@ -767,10 +783,15 @@ static int rtnl_net_getid(struct sk_buff *skb, struct nlmsghdr *nlh,
{
struct net *net = sock_net(skb->sk);
struct nlattr *tb[NETNSA_MAX + 1];
+ struct net_fill_args fillargs = {
+ .portid = NETLINK_CB(skb).portid,
+ .seq = nlh->nlmsg_seq,
+ .cmd = RTM_NEWNSID,
+ };
+ struct net *peer, *target = net;
struct nlattr *nla;
struct sk_buff *msg;
- struct net *peer;
- int err, id;
+ int err;
err = nlmsg_parse(nlh, sizeof(struct rtgenmsg), tb, NETNSA_MAX,
rtnl_net_policy, extack);
@@ -782,6 +803,11 @@ static int rtnl_net_getid(struct sk_buff *skb, struct nlmsghdr *nlh,
} else if (tb[NETNSA_FD]) {
peer = get_net_ns_by_fd(nla_get_u32(tb[NETNSA_FD]));
nla = tb[NETNSA_FD];
+ } else if (tb[NETNSA_NSID]) {
+ peer = get_net_ns_by_id(net, nla_get_u32(tb[NETNSA_NSID]));
+ if (!peer)
+ peer = ERR_PTR(-ENOENT);
+ nla = tb[NETNSA_NSID];
} else {
NL_SET_ERR_MSG(extack, "Peer netns reference is missing");
return -EINVAL;
@@ -793,15 +819,29 @@ static int rtnl_net_getid(struct sk_buff *skb, struct nlmsghdr *nlh,
return PTR_ERR(peer);
}
+ if (tb[NETNSA_TARGET_NSID]) {
+ int id = nla_get_s32(tb[NETNSA_TARGET_NSID]);
+
+ target = rtnl_get_net_ns_capable(NETLINK_CB(skb).sk, id);
+ if (IS_ERR(target)) {
+ NL_SET_BAD_ATTR(extack, tb[NETNSA_TARGET_NSID]);
+ NL_SET_ERR_MSG(extack,
+ "Target netns reference is invalid");
+ err = PTR_ERR(target);
+ goto out;
+ }
+ fillargs.add_ref = true;
+ fillargs.ref_nsid = peernet2id(net, peer);
+ }
+
msg = nlmsg_new(rtnl_net_get_size(), GFP_KERNEL);
if (!msg) {
err = -ENOMEM;
goto out;
}
- id = peernet2id(net, peer);
- err = rtnl_net_fill(msg, NETLINK_CB(skb).portid, nlh->nlmsg_seq, 0,
- RTM_NEWNSID, net, id);
+ fillargs.nsid = peernet2id(target, peer);
+ err = rtnl_net_fill(msg, &fillargs);
if (err < 0)
goto err_out;
@@ -811,14 +851,17 @@ static int rtnl_net_getid(struct sk_buff *skb, struct nlmsghdr *nlh,
err_out:
nlmsg_free(msg);
out:
+ if (fillargs.add_ref)
+ put_net(target);
put_net(peer);
return err;
}
struct rtnl_net_dump_cb {
- struct net *net;
+ struct net *tgt_net;
+ struct net *ref_net;
struct sk_buff *skb;
- struct netlink_callback *cb;
+ struct net_fill_args fillargs;
int idx;
int s_idx;
};
@@ -831,9 +874,10 @@ static int rtnl_net_dumpid_one(int id, void *peer, void *data)
if (net_cb->idx < net_cb->s_idx)
goto cont;
- ret = rtnl_net_fill(net_cb->skb, NETLINK_CB(net_cb->cb->skb).portid,
- net_cb->cb->nlh->nlmsg_seq, NLM_F_MULTI,
- RTM_NEWNSID, net_cb->net, id);
+ net_cb->fillargs.nsid = id;
+ if (net_cb->fillargs.add_ref)
+ net_cb->fillargs.ref_nsid = __peernet2id(net_cb->ref_net, peer);
+ ret = rtnl_net_fill(net_cb->skb, &net_cb->fillargs);
if (ret < 0)
return ret;
@@ -842,33 +886,96 @@ cont:
return 0;
}
+static int rtnl_valid_dump_net_req(const struct nlmsghdr *nlh, struct sock *sk,
+ struct rtnl_net_dump_cb *net_cb,
+ struct netlink_callback *cb)
+{
+ struct netlink_ext_ack *extack = cb->extack;
+ struct nlattr *tb[NETNSA_MAX + 1];
+ int err, i;
+
+ err = nlmsg_parse_strict(nlh, sizeof(struct rtgenmsg), tb, NETNSA_MAX,
+ rtnl_net_policy, extack);
+ if (err < 0)
+ return err;
+
+ for (i = 0; i <= NETNSA_MAX; i++) {
+ if (!tb[i])
+ continue;
+
+ if (i == NETNSA_TARGET_NSID) {
+ struct net *net;
+
+ net = rtnl_get_net_ns_capable(sk, nla_get_s32(tb[i]));
+ if (IS_ERR(net)) {
+ NL_SET_BAD_ATTR(extack, tb[i]);
+ NL_SET_ERR_MSG(extack,
+ "Invalid target network namespace id");
+ return PTR_ERR(net);
+ }
+ net_cb->fillargs.add_ref = true;
+ net_cb->ref_net = net_cb->tgt_net;
+ net_cb->tgt_net = net;
+ } else {
+ NL_SET_BAD_ATTR(extack, tb[i]);
+ NL_SET_ERR_MSG(extack,
+ "Unsupported attribute in dump request");
+ return -EINVAL;
+ }
+ }
+
+ return 0;
+}
+
static int rtnl_net_dumpid(struct sk_buff *skb, struct netlink_callback *cb)
{
- struct net *net = sock_net(skb->sk);
struct rtnl_net_dump_cb net_cb = {
- .net = net,
+ .tgt_net = sock_net(skb->sk),
.skb = skb,
- .cb = cb,
+ .fillargs = {
+ .portid = NETLINK_CB(cb->skb).portid,
+ .seq = cb->nlh->nlmsg_seq,
+ .flags = NLM_F_MULTI,
+ .cmd = RTM_NEWNSID,
+ },
.idx = 0,
.s_idx = cb->args[0],
};
+ int err = 0;
- if (cb->strict_check &&
- nlmsg_attrlen(cb->nlh, sizeof(struct rtgenmsg))) {
- NL_SET_ERR_MSG(cb->extack, "Unknown data in network namespace id dump request");
- return -EINVAL;
+ if (cb->strict_check) {
+ err = rtnl_valid_dump_net_req(cb->nlh, skb->sk, &net_cb, cb);
+ if (err < 0)
+ goto end;
}
- spin_lock_bh(&net->nsid_lock);
- idr_for_each(&net->netns_ids, rtnl_net_dumpid_one, &net_cb);
- spin_unlock_bh(&net->nsid_lock);
+ spin_lock_bh(&net_cb.tgt_net->nsid_lock);
+ if (net_cb.fillargs.add_ref &&
+ !net_eq(net_cb.ref_net, net_cb.tgt_net) &&
+ !spin_trylock_bh(&net_cb.ref_net->nsid_lock)) {
+ spin_unlock_bh(&net_cb.tgt_net->nsid_lock);
+ err = -EAGAIN;
+ goto end;
+ }
+ idr_for_each(&net_cb.tgt_net->netns_ids, rtnl_net_dumpid_one, &net_cb);
+ if (net_cb.fillargs.add_ref &&
+ !net_eq(net_cb.ref_net, net_cb.tgt_net))
+ spin_unlock_bh(&net_cb.ref_net->nsid_lock);
+ spin_unlock_bh(&net_cb.tgt_net->nsid_lock);
cb->args[0] = net_cb.idx;
- return skb->len;
+end:
+ if (net_cb.fillargs.add_ref)
+ put_net(net_cb.tgt_net);
+ return err < 0 ? err : skb->len;
}
static void rtnl_net_notifyid(struct net *net, int cmd, int id)
{
+ struct net_fill_args fillargs = {
+ .cmd = cmd,
+ .nsid = id,
+ };
struct sk_buff *msg;
int err = -ENOMEM;
@@ -876,7 +983,7 @@ static void rtnl_net_notifyid(struct net *net, int cmd, int id)
if (!msg)
goto out;
- err = rtnl_net_fill(msg, 0, 0, 0, cmd, net, id);
+ err = rtnl_net_fill(msg, &fillargs);
if (err < 0)
goto err_out;
@@ -917,7 +1024,8 @@ static int __init net_ns_init(void)
init_net_initialized = true;
up_write(&pernet_ops_rwsem);
- register_pernet_subsys(&net_ns_ops);
+ if (register_pernet_subsys(&net_ns_ops))
+ panic("Could not register network namespace subsystems");
rtnl_register(PF_UNSPEC, RTM_NEWNSID, rtnl_net_newid, NULL,
RTNL_FLAG_DOIT_UNLOCKED);
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index 464f0ff46c22..361aabffb8c0 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -663,7 +663,7 @@ int netpoll_setup(struct netpoll *np)
np_info(np, "device %s not up yet, forcing it\n", np->dev_name);
- err = dev_open(ndev);
+ err = dev_open(ndev, NULL);
if (err) {
np_err(np, "failed to open %s\n", ndev->name);
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 7819f7804eeb..48f61885fd6f 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -59,7 +59,7 @@
#include <net/rtnetlink.h>
#include <net/net_namespace.h>
-#define RTNL_MAX_TYPE 49
+#define RTNL_MAX_TYPE 50
#define RTNL_SLAVE_MAX_TYPE 36
struct rtnl_link {
@@ -2444,7 +2444,7 @@ static int do_setlink(const struct sk_buff *skb,
sa->sa_family = dev->type;
memcpy(sa->sa_data, nla_data(tb[IFLA_ADDRESS]),
dev->addr_len);
- err = dev_set_mac_address(dev, sa);
+ err = dev_set_mac_address(dev, sa, extack);
kfree(sa);
if (err)
goto errout;
@@ -2489,7 +2489,8 @@ static int do_setlink(const struct sk_buff *skb,
}
if (ifm->ifi_flags || ifm->ifi_change) {
- err = dev_change_flags(dev, rtnl_dev_combine_flags(dev, ifm));
+ err = dev_change_flags(dev, rtnl_dev_combine_flags(dev, ifm),
+ extack);
if (err < 0)
goto errout;
}
@@ -2870,7 +2871,8 @@ int rtnl_configure_link(struct net_device *dev, const struct ifinfomsg *ifm)
old_flags = dev->flags;
if (ifm && (ifm->ifi_flags || ifm->ifi_change)) {
- err = __dev_change_flags(dev, rtnl_dev_combine_flags(dev, ifm));
+ err = __dev_change_flags(dev, rtnl_dev_combine_flags(dev, ifm),
+ NULL);
if (err < 0)
return err;
}
@@ -2885,9 +2887,11 @@ int rtnl_configure_link(struct net_device *dev, const struct ifinfomsg *ifm)
}
EXPORT_SYMBOL(rtnl_configure_link);
-struct net_device *rtnl_create_link(struct net *net,
- const char *ifname, unsigned char name_assign_type,
- const struct rtnl_link_ops *ops, struct nlattr *tb[])
+struct net_device *rtnl_create_link(struct net *net, const char *ifname,
+ unsigned char name_assign_type,
+ const struct rtnl_link_ops *ops,
+ struct nlattr *tb[],
+ struct netlink_ext_ack *extack)
{
struct net_device *dev;
unsigned int num_tx_queues = 1;
@@ -2903,11 +2907,15 @@ struct net_device *rtnl_create_link(struct net *net,
else if (ops->get_num_rx_queues)
num_rx_queues = ops->get_num_rx_queues();
- if (num_tx_queues < 1 || num_tx_queues > 4096)
+ if (num_tx_queues < 1 || num_tx_queues > 4096) {
+ NL_SET_ERR_MSG(extack, "Invalid number of transmit queues");
return ERR_PTR(-EINVAL);
+ }
- if (num_rx_queues < 1 || num_rx_queues > 4096)
+ if (num_rx_queues < 1 || num_rx_queues > 4096) {
+ NL_SET_ERR_MSG(extack, "Invalid number of receive queues");
return ERR_PTR(-EINVAL);
+ }
dev = alloc_netdev_mqs(ops->priv_size, ifname, name_assign_type,
ops->setup, num_tx_queues, num_rx_queues);
@@ -2965,20 +2973,24 @@ static int rtnl_group_changelink(const struct sk_buff *skb,
return 0;
}
-static int rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh,
- struct netlink_ext_ack *extack)
+static int __rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh,
+ struct nlattr **attr, struct netlink_ext_ack *extack)
{
+ struct nlattr *slave_attr[RTNL_SLAVE_MAX_TYPE + 1];
+ unsigned char name_assign_type = NET_NAME_USER;
+ struct nlattr *linkinfo[IFLA_INFO_MAX + 1];
+ const struct rtnl_link_ops *m_ops = NULL;
+ struct net_device *master_dev = NULL;
struct net *net = sock_net(skb->sk);
const struct rtnl_link_ops *ops;
- const struct rtnl_link_ops *m_ops = NULL;
+ struct nlattr *tb[IFLA_MAX + 1];
+ struct net *dest_net, *link_net;
+ struct nlattr **slave_data;
+ char kind[MODULE_NAME_LEN];
struct net_device *dev;
- struct net_device *master_dev = NULL;
struct ifinfomsg *ifm;
- char kind[MODULE_NAME_LEN];
char ifname[IFNAMSIZ];
- struct nlattr *tb[IFLA_MAX+1];
- struct nlattr *linkinfo[IFLA_INFO_MAX+1];
- unsigned char name_assign_type = NET_NAME_USER;
+ struct nlattr **data;
int err;
#ifdef CONFIG_MODULES
@@ -3034,193 +3046,200 @@ replay:
ops = NULL;
}
- if (1) {
- struct nlattr *attr[RTNL_MAX_TYPE + 1];
- struct nlattr *slave_attr[RTNL_SLAVE_MAX_TYPE + 1];
- struct nlattr **data = NULL;
- struct nlattr **slave_data = NULL;
- struct net *dest_net, *link_net = NULL;
-
- if (ops) {
- if (ops->maxtype > RTNL_MAX_TYPE)
- return -EINVAL;
+ data = NULL;
+ if (ops) {
+ if (ops->maxtype > RTNL_MAX_TYPE)
+ return -EINVAL;
- if (ops->maxtype && linkinfo[IFLA_INFO_DATA]) {
- err = nla_parse_nested(attr, ops->maxtype,
- linkinfo[IFLA_INFO_DATA],
- ops->policy, NULL);
- if (err < 0)
- return err;
- data = attr;
- }
- if (ops->validate) {
- err = ops->validate(tb, data, extack);
- if (err < 0)
- return err;
- }
+ if (ops->maxtype && linkinfo[IFLA_INFO_DATA]) {
+ err = nla_parse_nested(attr, ops->maxtype,
+ linkinfo[IFLA_INFO_DATA],
+ ops->policy, extack);
+ if (err < 0)
+ return err;
+ data = attr;
+ }
+ if (ops->validate) {
+ err = ops->validate(tb, data, extack);
+ if (err < 0)
+ return err;
}
+ }
- if (m_ops) {
- if (m_ops->slave_maxtype > RTNL_SLAVE_MAX_TYPE)
- return -EINVAL;
+ slave_data = NULL;
+ if (m_ops) {
+ if (m_ops->slave_maxtype > RTNL_SLAVE_MAX_TYPE)
+ return -EINVAL;
- if (m_ops->slave_maxtype &&
- linkinfo[IFLA_INFO_SLAVE_DATA]) {
- err = nla_parse_nested(slave_attr,
- m_ops->slave_maxtype,
- linkinfo[IFLA_INFO_SLAVE_DATA],
- m_ops->slave_policy,
- NULL);
- if (err < 0)
- return err;
- slave_data = slave_attr;
- }
+ if (m_ops->slave_maxtype &&
+ linkinfo[IFLA_INFO_SLAVE_DATA]) {
+ err = nla_parse_nested(slave_attr, m_ops->slave_maxtype,
+ linkinfo[IFLA_INFO_SLAVE_DATA],
+ m_ops->slave_policy, extack);
+ if (err < 0)
+ return err;
+ slave_data = slave_attr;
}
+ }
- if (dev) {
- int status = 0;
-
- if (nlh->nlmsg_flags & NLM_F_EXCL)
- return -EEXIST;
- if (nlh->nlmsg_flags & NLM_F_REPLACE)
- return -EOPNOTSUPP;
+ if (dev) {
+ int status = 0;
- if (linkinfo[IFLA_INFO_DATA]) {
- if (!ops || ops != dev->rtnl_link_ops ||
- !ops->changelink)
- return -EOPNOTSUPP;
+ if (nlh->nlmsg_flags & NLM_F_EXCL)
+ return -EEXIST;
+ if (nlh->nlmsg_flags & NLM_F_REPLACE)
+ return -EOPNOTSUPP;
- err = ops->changelink(dev, tb, data, extack);
- if (err < 0)
- return err;
- status |= DO_SETLINK_NOTIFY;
- }
+ if (linkinfo[IFLA_INFO_DATA]) {
+ if (!ops || ops != dev->rtnl_link_ops ||
+ !ops->changelink)
+ return -EOPNOTSUPP;
- if (linkinfo[IFLA_INFO_SLAVE_DATA]) {
- if (!m_ops || !m_ops->slave_changelink)
- return -EOPNOTSUPP;
+ err = ops->changelink(dev, tb, data, extack);
+ if (err < 0)
+ return err;
+ status |= DO_SETLINK_NOTIFY;
+ }
- err = m_ops->slave_changelink(master_dev, dev,
- tb, slave_data,
- extack);
- if (err < 0)
- return err;
- status |= DO_SETLINK_NOTIFY;
- }
+ if (linkinfo[IFLA_INFO_SLAVE_DATA]) {
+ if (!m_ops || !m_ops->slave_changelink)
+ return -EOPNOTSUPP;
- return do_setlink(skb, dev, ifm, extack, tb, ifname,
- status);
+ err = m_ops->slave_changelink(master_dev, dev, tb,
+ slave_data, extack);
+ if (err < 0)
+ return err;
+ status |= DO_SETLINK_NOTIFY;
}
- if (!(nlh->nlmsg_flags & NLM_F_CREATE)) {
- if (ifm->ifi_index == 0 && tb[IFLA_GROUP])
- return rtnl_group_changelink(skb, net,
+ return do_setlink(skb, dev, ifm, extack, tb, ifname, status);
+ }
+
+ if (!(nlh->nlmsg_flags & NLM_F_CREATE)) {
+ if (ifm->ifi_index == 0 && tb[IFLA_GROUP])
+ return rtnl_group_changelink(skb, net,
nla_get_u32(tb[IFLA_GROUP]),
ifm, extack, tb);
- return -ENODEV;
- }
+ return -ENODEV;
+ }
- if (tb[IFLA_MAP] || tb[IFLA_PROTINFO])
- return -EOPNOTSUPP;
+ if (tb[IFLA_MAP] || tb[IFLA_PROTINFO])
+ return -EOPNOTSUPP;
- if (!ops) {
+ if (!ops) {
#ifdef CONFIG_MODULES
- if (kind[0]) {
- __rtnl_unlock();
- request_module("rtnl-link-%s", kind);
- rtnl_lock();
- ops = rtnl_link_ops_get(kind);
- if (ops)
- goto replay;
- }
-#endif
- return -EOPNOTSUPP;
+ if (kind[0]) {
+ __rtnl_unlock();
+ request_module("rtnl-link-%s", kind);
+ rtnl_lock();
+ ops = rtnl_link_ops_get(kind);
+ if (ops)
+ goto replay;
}
+#endif
+ NL_SET_ERR_MSG(extack, "Unknown device type");
+ return -EOPNOTSUPP;
+ }
- if (!ops->setup)
- return -EOPNOTSUPP;
-
- if (!ifname[0]) {
- snprintf(ifname, IFNAMSIZ, "%s%%d", ops->kind);
- name_assign_type = NET_NAME_ENUM;
- }
+ if (!ops->setup)
+ return -EOPNOTSUPP;
- dest_net = rtnl_link_get_net_capable(skb, net, tb, CAP_NET_ADMIN);
- if (IS_ERR(dest_net))
- return PTR_ERR(dest_net);
+ if (!ifname[0]) {
+ snprintf(ifname, IFNAMSIZ, "%s%%d", ops->kind);
+ name_assign_type = NET_NAME_ENUM;
+ }
- if (tb[IFLA_LINK_NETNSID]) {
- int id = nla_get_s32(tb[IFLA_LINK_NETNSID]);
+ dest_net = rtnl_link_get_net_capable(skb, net, tb, CAP_NET_ADMIN);
+ if (IS_ERR(dest_net))
+ return PTR_ERR(dest_net);
- link_net = get_net_ns_by_id(dest_net, id);
- if (!link_net) {
- err = -EINVAL;
- goto out;
- }
- err = -EPERM;
- if (!netlink_ns_capable(skb, link_net->user_ns, CAP_NET_ADMIN))
- goto out;
- }
+ if (tb[IFLA_LINK_NETNSID]) {
+ int id = nla_get_s32(tb[IFLA_LINK_NETNSID]);
- dev = rtnl_create_link(link_net ? : dest_net, ifname,
- name_assign_type, ops, tb);
- if (IS_ERR(dev)) {
- err = PTR_ERR(dev);
+ link_net = get_net_ns_by_id(dest_net, id);
+ if (!link_net) {
+ NL_SET_ERR_MSG(extack, "Unknown network namespace id");
+ err = -EINVAL;
goto out;
}
+ err = -EPERM;
+ if (!netlink_ns_capable(skb, link_net->user_ns, CAP_NET_ADMIN))
+ goto out;
+ } else {
+ link_net = NULL;
+ }
- dev->ifindex = ifm->ifi_index;
+ dev = rtnl_create_link(link_net ? : dest_net, ifname,
+ name_assign_type, ops, tb, extack);
+ if (IS_ERR(dev)) {
+ err = PTR_ERR(dev);
+ goto out;
+ }
- if (ops->newlink) {
- err = ops->newlink(link_net ? : net, dev, tb, data,
- extack);
- /* Drivers should call free_netdev() in ->destructor
- * and unregister it on failure after registration
- * so that device could be finally freed in rtnl_unlock.
- */
- if (err < 0) {
- /* If device is not registered at all, free it now */
- if (dev->reg_state == NETREG_UNINITIALIZED)
- free_netdev(dev);
- goto out;
- }
- } else {
- err = register_netdevice(dev);
- if (err < 0) {
+ dev->ifindex = ifm->ifi_index;
+
+ if (ops->newlink) {
+ err = ops->newlink(link_net ? : net, dev, tb, data, extack);
+ /* Drivers should call free_netdev() in ->destructor
+ * and unregister it on failure after registration
+ * so that device could be finally freed in rtnl_unlock.
+ */
+ if (err < 0) {
+ /* If device is not registered at all, free it now */
+ if (dev->reg_state == NETREG_UNINITIALIZED)
free_netdev(dev);
- goto out;
- }
+ goto out;
}
- err = rtnl_configure_link(dev, ifm);
+ } else {
+ err = register_netdevice(dev);
+ if (err < 0) {
+ free_netdev(dev);
+ goto out;
+ }
+ }
+ err = rtnl_configure_link(dev, ifm);
+ if (err < 0)
+ goto out_unregister;
+ if (link_net) {
+ err = dev_change_net_namespace(dev, dest_net, ifname);
if (err < 0)
goto out_unregister;
- if (link_net) {
- err = dev_change_net_namespace(dev, dest_net, ifname);
- if (err < 0)
- goto out_unregister;
- }
- if (tb[IFLA_MASTER]) {
- err = do_set_master(dev, nla_get_u32(tb[IFLA_MASTER]),
- extack);
- if (err)
- goto out_unregister;
- }
+ }
+ if (tb[IFLA_MASTER]) {
+ err = do_set_master(dev, nla_get_u32(tb[IFLA_MASTER]), extack);
+ if (err)
+ goto out_unregister;
+ }
out:
- if (link_net)
- put_net(link_net);
- put_net(dest_net);
- return err;
+ if (link_net)
+ put_net(link_net);
+ put_net(dest_net);
+ return err;
out_unregister:
- if (ops->newlink) {
- LIST_HEAD(list_kill);
+ if (ops->newlink) {
+ LIST_HEAD(list_kill);
- ops->dellink(dev, &list_kill);
- unregister_netdevice_many(&list_kill);
- } else {
- unregister_netdevice(dev);
- }
- goto out;
+ ops->dellink(dev, &list_kill);
+ unregister_netdevice_many(&list_kill);
+ } else {
+ unregister_netdevice(dev);
}
+ goto out;
+}
+
+static int rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh,
+ struct netlink_ext_ack *extack)
+{
+ struct nlattr **attr;
+ int ret;
+
+ attr = kmalloc_array(RTNL_MAX_TYPE + 1, sizeof(*attr), GFP_KERNEL);
+ if (!attr)
+ return -ENOMEM;
+
+ ret = __rtnl_newlink(skb, nlh, attr, extack);
+ kfree(attr);
+ return ret;
}
static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr *nlh,
@@ -4002,6 +4021,160 @@ out:
return skb->len;
}
+static int valid_fdb_get_strict(const struct nlmsghdr *nlh,
+ struct nlattr **tb, u8 *ndm_flags,
+ int *br_idx, int *brport_idx, u8 **addr,
+ u16 *vid, struct netlink_ext_ack *extack)
+{
+ struct ndmsg *ndm;
+ int err, i;
+
+ if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ndm))) {
+ NL_SET_ERR_MSG(extack, "Invalid header for fdb get request");
+ return -EINVAL;
+ }
+
+ ndm = nlmsg_data(nlh);
+ if (ndm->ndm_pad1 || ndm->ndm_pad2 || ndm->ndm_state ||
+ ndm->ndm_type) {
+ NL_SET_ERR_MSG(extack, "Invalid values in header for fdb get request");
+ return -EINVAL;
+ }
+
+ if (ndm->ndm_flags & ~(NTF_MASTER | NTF_SELF)) {
+ NL_SET_ERR_MSG(extack, "Invalid flags in header for fdb get request");
+ return -EINVAL;
+ }
+
+ err = nlmsg_parse_strict(nlh, sizeof(struct ndmsg), tb, NDA_MAX,
+ nda_policy, extack);
+ if (err < 0)
+ return err;
+
+ *ndm_flags = ndm->ndm_flags;
+ *brport_idx = ndm->ndm_ifindex;
+ for (i = 0; i <= NDA_MAX; ++i) {
+ if (!tb[i])
+ continue;
+
+ switch (i) {
+ case NDA_MASTER:
+ *br_idx = nla_get_u32(tb[i]);
+ break;
+ case NDA_LLADDR:
+ if (nla_len(tb[i]) != ETH_ALEN) {
+ NL_SET_ERR_MSG(extack, "Invalid address in fdb get request");
+ return -EINVAL;
+ }
+ *addr = nla_data(tb[i]);
+ break;
+ case NDA_VLAN:
+ err = fdb_vid_parse(tb[i], vid, extack);
+ if (err)
+ return err;
+ break;
+ case NDA_VNI:
+ break;
+ default:
+ NL_SET_ERR_MSG(extack, "Unsupported attribute in fdb get request");
+ return -EINVAL;
+ }
+ }
+
+ return 0;
+}
+
+static int rtnl_fdb_get(struct sk_buff *in_skb, struct nlmsghdr *nlh,
+ struct netlink_ext_ack *extack)
+{
+ struct net_device *dev = NULL, *br_dev = NULL;
+ const struct net_device_ops *ops = NULL;
+ struct net *net = sock_net(in_skb->sk);
+ struct nlattr *tb[NDA_MAX + 1];
+ struct sk_buff *skb;
+ int brport_idx = 0;
+ u8 ndm_flags = 0;
+ int br_idx = 0;
+ u8 *addr = NULL;
+ u16 vid = 0;
+ int err;
+
+ err = valid_fdb_get_strict(nlh, tb, &ndm_flags, &br_idx,
+ &brport_idx, &addr, &vid, extack);
+ if (err < 0)
+ return err;
+
+ if (brport_idx) {
+ dev = __dev_get_by_index(net, brport_idx);
+ if (!dev) {
+ NL_SET_ERR_MSG(extack, "Unknown device ifindex");
+ return -ENODEV;
+ }
+ }
+
+ if (br_idx) {
+ if (dev) {
+ NL_SET_ERR_MSG(extack, "Master and device are mutually exclusive");
+ return -EINVAL;
+ }
+
+ br_dev = __dev_get_by_index(net, br_idx);
+ if (!br_dev) {
+ NL_SET_ERR_MSG(extack, "Invalid master ifindex");
+ return -EINVAL;
+ }
+ ops = br_dev->netdev_ops;
+ }
+
+ if (dev) {
+ if (!ndm_flags || (ndm_flags & NTF_MASTER)) {
+ if (!(dev->priv_flags & IFF_BRIDGE_PORT)) {
+ NL_SET_ERR_MSG(extack, "Device is not a bridge port");
+ return -EINVAL;
+ }
+ br_dev = netdev_master_upper_dev_get(dev);
+ if (!br_dev) {
+ NL_SET_ERR_MSG(extack, "Master of device not found");
+ return -EINVAL;
+ }
+ ops = br_dev->netdev_ops;
+ } else {
+ if (!(ndm_flags & NTF_SELF)) {
+ NL_SET_ERR_MSG(extack, "Missing NTF_SELF");
+ return -EINVAL;
+ }
+ ops = dev->netdev_ops;
+ }
+ }
+
+ if (!br_dev && !dev) {
+ NL_SET_ERR_MSG(extack, "No device specified");
+ return -ENODEV;
+ }
+
+ if (!ops || !ops->ndo_fdb_get) {
+ NL_SET_ERR_MSG(extack, "Fdb get operation not supported by device");
+ return -EOPNOTSUPP;
+ }
+
+ skb = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL);
+ if (!skb)
+ return -ENOBUFS;
+
+ if (br_dev)
+ dev = br_dev;
+ err = ops->ndo_fdb_get(skb, tb, dev, addr, vid,
+ NETLINK_CB(in_skb).portid,
+ nlh->nlmsg_seq, extack);
+ if (err)
+ goto out;
+
+ return rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid);
+out:
+ kfree_skb(skb);
+ return err;
+}
+
static int brport_nla_put_flag(struct sk_buff *skb, u32 flags, u32 mask,
unsigned int attrnum, unsigned int flag)
{
@@ -4313,7 +4486,8 @@ static int rtnl_bridge_setlink(struct sk_buff *skb, struct nlmsghdr *nlh,
goto out;
}
- err = br_dev->netdev_ops->ndo_bridge_setlink(dev, nlh, flags);
+ err = br_dev->netdev_ops->ndo_bridge_setlink(dev, nlh, flags,
+ extack);
if (err)
goto out;
@@ -4325,7 +4499,8 @@ static int rtnl_bridge_setlink(struct sk_buff *skb, struct nlmsghdr *nlh,
err = -EOPNOTSUPP;
else
err = dev->netdev_ops->ndo_bridge_setlink(dev, nlh,
- flags);
+ flags,
+ extack);
if (!err) {
flags &= ~BRIDGE_FLAGS_SELF;
@@ -5060,7 +5235,7 @@ void __init rtnetlink_init(void)
rtnl_register(PF_BRIDGE, RTM_NEWNEIGH, rtnl_fdb_add, NULL, 0);
rtnl_register(PF_BRIDGE, RTM_DELNEIGH, rtnl_fdb_del, NULL, 0);
- rtnl_register(PF_BRIDGE, RTM_GETNEIGH, NULL, rtnl_fdb_dump, 0);
+ rtnl_register(PF_BRIDGE, RTM_GETNEIGH, rtnl_fdb_get, rtnl_fdb_dump, 0);
rtnl_register(PF_BRIDGE, RTM_GETLINK, NULL, rtnl_bridge_getlink, 0);
rtnl_register(PF_BRIDGE, RTM_DELLINK, rtnl_bridge_dellink, NULL, 0);
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index a8217e221e19..37317ffec146 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -79,6 +79,9 @@
struct kmem_cache *skbuff_head_cache __ro_after_init;
static struct kmem_cache *skbuff_fclone_cache __ro_after_init;
+#ifdef CONFIG_SKB_EXTENSIONS
+static struct kmem_cache *skbuff_ext_cache __ro_after_init;
+#endif
int sysctl_max_skb_frags __read_mostly = MAX_SKB_FRAGS;
EXPORT_SYMBOL(sysctl_max_skb_frags);
@@ -606,7 +609,6 @@ fastpath:
void skb_release_head_state(struct sk_buff *skb)
{
skb_dst_drop(skb);
- secpath_reset(skb);
if (skb->destructor) {
WARN_ON(in_irq());
skb->destructor(skb);
@@ -614,9 +616,7 @@ void skb_release_head_state(struct sk_buff *skb)
#if IS_ENABLED(CONFIG_NF_CONNTRACK)
nf_conntrack_put(skb_nfct(skb));
#endif
-#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
- nf_bridge_put(skb->nf_bridge);
-#endif
+ skb_ext_put(skb);
}
/* Free everything but the sk_buff shell. */
@@ -796,9 +796,7 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old)
new->dev = old->dev;
memcpy(new->cb, old->cb, sizeof(old->cb));
skb_dst_copy(new, old);
-#ifdef CONFIG_XFRM
- new->sp = secpath_get(old->sp);
-#endif
+ __skb_ext_copy(new, old);
__nf_copy(new, old, false);
/* Note : this field could be in headers_start/headers_end section
@@ -1089,7 +1087,7 @@ void sock_zerocopy_put(struct ubuf_info *uarg)
}
EXPORT_SYMBOL_GPL(sock_zerocopy_put);
-void sock_zerocopy_put_abort(struct ubuf_info *uarg)
+void sock_zerocopy_put_abort(struct ubuf_info *uarg, bool have_uref)
{
if (uarg) {
struct sock *sk = skb_from_uarg(uarg)->sk;
@@ -1097,7 +1095,8 @@ void sock_zerocopy_put_abort(struct ubuf_info *uarg)
atomic_dec(&sk->sk_zckey);
uarg->len--;
- sock_zerocopy_put(uarg);
+ if (have_uref)
+ sock_zerocopy_put(uarg);
}
}
EXPORT_SYMBOL_GPL(sock_zerocopy_put_abort);
@@ -1105,6 +1104,12 @@ EXPORT_SYMBOL_GPL(sock_zerocopy_put_abort);
extern int __zerocopy_sg_from_iter(struct sock *sk, struct sk_buff *skb,
struct iov_iter *from, size_t length);
+int skb_zerocopy_iter_dgram(struct sk_buff *skb, struct msghdr *msg, int len)
+{
+ return __zerocopy_sg_from_iter(skb->sk, skb, &msg->msg_iter, len);
+}
+EXPORT_SYMBOL_GPL(skb_zerocopy_iter_dgram);
+
int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb,
struct msghdr *msg, int len,
struct ubuf_info *uarg)
@@ -1131,7 +1136,7 @@ int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb,
return err;
}
- skb_zcopy_set(skb, uarg);
+ skb_zcopy_set(skb, uarg, NULL);
return skb->len - orig_len;
}
EXPORT_SYMBOL_GPL(skb_zerocopy_iter_stream);
@@ -1151,7 +1156,7 @@ static int skb_zerocopy_clone(struct sk_buff *nskb, struct sk_buff *orig,
if (skb_copy_ubufs(nskb, GFP_ATOMIC))
return -EIO;
}
- skb_zcopy_set(nskb, skb_uarg(orig));
+ skb_zcopy_set(nskb, skb_uarg(orig), NULL);
}
return 0;
}
@@ -1925,8 +1930,6 @@ void *__pskb_pull_tail(struct sk_buff *skb, int delta)
struct sk_buff *insp = NULL;
do {
- BUG_ON(!list);
-
if (list->len <= eat) {
/* Eaten as whole. */
eat -= list->len;
@@ -2366,19 +2369,6 @@ error:
}
EXPORT_SYMBOL_GPL(skb_send_sock_locked);
-/* Send skb data on a socket. */
-int skb_send_sock(struct sock *sk, struct sk_buff *skb, int offset, int len)
-{
- int ret = 0;
-
- lock_sock(sk);
- ret = skb_send_sock_locked(sk, skb, offset, len);
- release_sock(sk);
-
- return ret;
-}
-EXPORT_SYMBOL_GPL(skb_send_sock);
-
/**
* skb_store_bits - store bits from kernel buffer to skb
* @skb: destination buffer
@@ -2645,6 +2635,65 @@ __wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset,
}
EXPORT_SYMBOL(skb_copy_and_csum_bits);
+__sum16 __skb_checksum_complete_head(struct sk_buff *skb, int len)
+{
+ __sum16 sum;
+
+ sum = csum_fold(skb_checksum(skb, 0, len, skb->csum));
+ /* See comments in __skb_checksum_complete(). */
+ if (likely(!sum)) {
+ if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE) &&
+ !skb->csum_complete_sw)
+ netdev_rx_csum_fault(skb->dev, skb);
+ }
+ if (!skb_shared(skb))
+ skb->csum_valid = !sum;
+ return sum;
+}
+EXPORT_SYMBOL(__skb_checksum_complete_head);
+
+/* This function assumes skb->csum already holds pseudo header's checksum,
+ * which has been changed from the hardware checksum, for example, by
+ * __skb_checksum_validate_complete(). And, the original skb->csum must
+ * have been validated unsuccessfully for CHECKSUM_COMPLETE case.
+ *
+ * It returns non-zero if the recomputed checksum is still invalid, otherwise
+ * zero. The new checksum is stored back into skb->csum unless the skb is
+ * shared.
+ */
+__sum16 __skb_checksum_complete(struct sk_buff *skb)
+{
+ __wsum csum;
+ __sum16 sum;
+
+ csum = skb_checksum(skb, 0, skb->len, 0);
+
+ sum = csum_fold(csum_add(skb->csum, csum));
+ /* This check is inverted, because we already knew the hardware
+ * checksum is invalid before calling this function. So, if the
+ * re-computed checksum is valid instead, then we have a mismatch
+ * between the original skb->csum and skb_checksum(). This means either
+ * the original hardware checksum is incorrect or we screw up skb->csum
+ * when moving skb->data around.
+ */
+ if (likely(!sum)) {
+ if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE) &&
+ !skb->csum_complete_sw)
+ netdev_rx_csum_fault(skb->dev, skb);
+ }
+
+ if (!skb_shared(skb)) {
+ /* Save full packet checksum */
+ skb->csum = csum;
+ skb->ip_summed = CHECKSUM_COMPLETE;
+ skb->csum_complete_sw = 1;
+ skb->csum_valid = !sum;
+ }
+
+ return sum;
+}
+EXPORT_SYMBOL(__skb_checksum_complete);
+
static __wsum warn_crc32c_csum_update(const void *buff, int len, __wsum sum)
{
net_warn_ratelimited(
@@ -2962,28 +3011,6 @@ void skb_append(struct sk_buff *old, struct sk_buff *newsk, struct sk_buff_head
}
EXPORT_SYMBOL(skb_append);
-/**
- * skb_insert - insert a buffer
- * @old: buffer to insert before
- * @newsk: buffer to insert
- * @list: list to use
- *
- * Place a packet before a given packet in a list. The list locks are
- * taken and this function is atomic with respect to other list locked
- * calls.
- *
- * A buffer cannot be placed on two lists at the same time.
- */
-void skb_insert(struct sk_buff *old, struct sk_buff *newsk, struct sk_buff_head *list)
-{
- unsigned long flags;
-
- spin_lock_irqsave(&list->lock, flags);
- __skb_insert(newsk, old->prev, old, list);
- spin_unlock_irqrestore(&list->lock, flags);
-}
-EXPORT_SYMBOL(skb_insert);
-
static inline void skb_split_inside_header(struct sk_buff *skb,
struct sk_buff* skb1,
const u32 len, const int pos)
@@ -3873,6 +3900,46 @@ done:
}
EXPORT_SYMBOL_GPL(skb_gro_receive);
+#ifdef CONFIG_SKB_EXTENSIONS
+#define SKB_EXT_ALIGN_VALUE 8
+#define SKB_EXT_CHUNKSIZEOF(x) (ALIGN((sizeof(x)), SKB_EXT_ALIGN_VALUE) / SKB_EXT_ALIGN_VALUE)
+
+static const u8 skb_ext_type_len[] = {
+#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
+ [SKB_EXT_BRIDGE_NF] = SKB_EXT_CHUNKSIZEOF(struct nf_bridge_info),
+#endif
+#ifdef CONFIG_XFRM
+ [SKB_EXT_SEC_PATH] = SKB_EXT_CHUNKSIZEOF(struct sec_path),
+#endif
+};
+
+static __always_inline unsigned int skb_ext_total_length(void)
+{
+ return SKB_EXT_CHUNKSIZEOF(struct skb_ext) +
+#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
+ skb_ext_type_len[SKB_EXT_BRIDGE_NF] +
+#endif
+#ifdef CONFIG_XFRM
+ skb_ext_type_len[SKB_EXT_SEC_PATH] +
+#endif
+ 0;
+}
+
+static void skb_extensions_init(void)
+{
+ BUILD_BUG_ON(SKB_EXT_NUM >= 8);
+ BUILD_BUG_ON(skb_ext_total_length() > 255);
+
+ skbuff_ext_cache = kmem_cache_create("skbuff_ext_cache",
+ SKB_EXT_ALIGN_VALUE * skb_ext_total_length(),
+ 0,
+ SLAB_HWCACHE_ALIGN|SLAB_PANIC,
+ NULL);
+}
+#else
+static void skb_extensions_init(void) {}
+#endif
+
void __init skb_init(void)
{
skbuff_head_cache = kmem_cache_create_usercopy("skbuff_head_cache",
@@ -3887,6 +3954,7 @@ void __init skb_init(void)
0,
SLAB_HWCACHE_ALIGN|SLAB_PANIC,
NULL);
+ skb_extensions_init();
}
static int
@@ -4856,7 +4924,7 @@ void skb_scrub_packet(struct sk_buff *skb, bool xnet)
#ifdef CONFIG_NET_SWITCHDEV
skb->offload_fwd_mark = 0;
- skb->offload_mr_fwd_mark = 0;
+ skb->offload_l3_fwd_mark = 0;
#endif
if (!xnet)
@@ -5128,7 +5196,7 @@ int skb_vlan_pop(struct sk_buff *skb)
int err;
if (likely(skb_vlan_tag_present(skb))) {
- skb->vlan_tci = 0;
+ __vlan_hwaccel_clear_tag(skb);
} else {
if (unlikely(!eth_type_vlan(skb->protocol)))
return 0;
@@ -5525,3 +5593,148 @@ void skb_condense(struct sk_buff *skb)
*/
skb->truesize = SKB_TRUESIZE(skb_end_offset(skb));
}
+
+#ifdef CONFIG_SKB_EXTENSIONS
+static void *skb_ext_get_ptr(struct skb_ext *ext, enum skb_ext_id id)
+{
+ return (void *)ext + (ext->offset[id] * SKB_EXT_ALIGN_VALUE);
+}
+
+static struct skb_ext *skb_ext_alloc(void)
+{
+ struct skb_ext *new = kmem_cache_alloc(skbuff_ext_cache, GFP_ATOMIC);
+
+ if (new) {
+ memset(new->offset, 0, sizeof(new->offset));
+ refcount_set(&new->refcnt, 1);
+ }
+
+ return new;
+}
+
+static struct skb_ext *skb_ext_maybe_cow(struct skb_ext *old,
+ unsigned int old_active)
+{
+ struct skb_ext *new;
+
+ if (refcount_read(&old->refcnt) == 1)
+ return old;
+
+ new = kmem_cache_alloc(skbuff_ext_cache, GFP_ATOMIC);
+ if (!new)
+ return NULL;
+
+ memcpy(new, old, old->chunks * SKB_EXT_ALIGN_VALUE);
+ refcount_set(&new->refcnt, 1);
+
+#ifdef CONFIG_XFRM
+ if (old_active & (1 << SKB_EXT_SEC_PATH)) {
+ struct sec_path *sp = skb_ext_get_ptr(old, SKB_EXT_SEC_PATH);
+ unsigned int i;
+
+ for (i = 0; i < sp->len; i++)
+ xfrm_state_hold(sp->xvec[i]);
+ }
+#endif
+ __skb_ext_put(old);
+ return new;
+}
+
+/**
+ * skb_ext_add - allocate space for given extension, COW if needed
+ * @skb: buffer
+ * @id: extension to allocate space for
+ *
+ * Allocates enough space for the given extension.
+ * If the extension is already present, a pointer to that extension
+ * is returned.
+ *
+ * If the skb was cloned, COW applies and the returned memory can be
+ * modified without changing the extension space of clones buffers.
+ *
+ * Returns pointer to the extension or NULL on allocation failure.
+ */
+void *skb_ext_add(struct sk_buff *skb, enum skb_ext_id id)
+{
+ struct skb_ext *new, *old = NULL;
+ unsigned int newlen, newoff;
+
+ if (skb->active_extensions) {
+ old = skb->extensions;
+
+ new = skb_ext_maybe_cow(old, skb->active_extensions);
+ if (!new)
+ return NULL;
+
+ if (__skb_ext_exist(new, id))
+ goto set_active;
+
+ newoff = new->chunks;
+ } else {
+ newoff = SKB_EXT_CHUNKSIZEOF(*new);
+
+ new = skb_ext_alloc();
+ if (!new)
+ return NULL;
+ }
+
+ newlen = newoff + skb_ext_type_len[id];
+ new->chunks = newlen;
+ new->offset[id] = newoff;
+set_active:
+ skb->extensions = new;
+ skb->active_extensions |= 1 << id;
+ return skb_ext_get_ptr(new, id);
+}
+EXPORT_SYMBOL(skb_ext_add);
+
+#ifdef CONFIG_XFRM
+static void skb_ext_put_sp(struct sec_path *sp)
+{
+ unsigned int i;
+
+ for (i = 0; i < sp->len; i++)
+ xfrm_state_put(sp->xvec[i]);
+}
+#endif
+
+void __skb_ext_del(struct sk_buff *skb, enum skb_ext_id id)
+{
+ struct skb_ext *ext = skb->extensions;
+
+ skb->active_extensions &= ~(1 << id);
+ if (skb->active_extensions == 0) {
+ skb->extensions = NULL;
+ __skb_ext_put(ext);
+#ifdef CONFIG_XFRM
+ } else if (id == SKB_EXT_SEC_PATH &&
+ refcount_read(&ext->refcnt) == 1) {
+ struct sec_path *sp = skb_ext_get_ptr(ext, SKB_EXT_SEC_PATH);
+
+ skb_ext_put_sp(sp);
+ sp->len = 0;
+#endif
+ }
+}
+EXPORT_SYMBOL(__skb_ext_del);
+
+void __skb_ext_put(struct skb_ext *ext)
+{
+ /* If this is last clone, nothing can increment
+ * it after check passes. Avoids one atomic op.
+ */
+ if (refcount_read(&ext->refcnt) == 1)
+ goto free_now;
+
+ if (!refcount_dec_and_test(&ext->refcnt))
+ return;
+free_now:
+#ifdef CONFIG_XFRM
+ if (__skb_ext_exist(ext, SKB_EXT_SEC_PATH))
+ skb_ext_put_sp(skb_ext_get_ptr(ext, SKB_EXT_SEC_PATH));
+#endif
+
+ kmem_cache_free(skbuff_ext_cache, ext);
+}
+EXPORT_SYMBOL(__skb_ext_put);
+#endif /* CONFIG_SKB_EXTENSIONS */
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index abaa5f48d3ec..d6d5c20d7044 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -406,7 +406,7 @@ static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb)
msg->skb = skb;
sk_psock_queue_msg(psock, msg);
- sk->sk_data_ready(sk);
+ sk_psock_data_ready(sk, psock);
return copied;
}
@@ -575,6 +575,7 @@ void sk_psock_drop(struct sock *sk, struct sk_psock *psock)
{
rcu_assign_sk_user_data(sk, NULL);
sk_psock_cork_free(psock);
+ sk_psock_zap_ingress(psock);
sk_psock_restore_proto(sk, psock);
write_lock_bh(&sk->sk_callback_lock);
@@ -672,6 +673,22 @@ static void sk_psock_verdict_apply(struct sk_psock *psock,
bool ingress;
switch (verdict) {
+ case __SK_PASS:
+ sk_other = psock->sk;
+ if (sock_flag(sk_other, SOCK_DEAD) ||
+ !sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) {
+ goto out_free;
+ }
+ if (atomic_read(&sk_other->sk_rmem_alloc) <=
+ sk_other->sk_rcvbuf) {
+ struct tcp_skb_cb *tcp = TCP_SKB_CB(skb);
+
+ tcp->bpf.flags |= BPF_F_INGRESS;
+ skb_queue_tail(&psock->ingress_skb, skb);
+ schedule_work(&psock->work);
+ break;
+ }
+ goto out_free;
case __SK_REDIRECT:
sk_other = tcp_skb_bpf_redirect_fetch(skb);
if (unlikely(!sk_other))
@@ -738,7 +755,7 @@ static int sk_psock_strp_parse(struct strparser *strp, struct sk_buff *skb)
}
/* Called with socket lock held. */
-static void sk_psock_data_ready(struct sock *sk)
+static void sk_psock_strp_data_ready(struct sock *sk)
{
struct sk_psock *psock;
@@ -786,7 +803,7 @@ void sk_psock_start_strp(struct sock *sk, struct sk_psock *psock)
return;
parser->saved_data_ready = sk->sk_data_ready;
- sk->sk_data_ready = sk_psock_data_ready;
+ sk->sk_data_ready = sk_psock_strp_data_ready;
sk->sk_write_space = sk_psock_write_space;
parser->enabled = true;
}
diff --git a/net/core/sock.c b/net/core/sock.c
index 080a880a1761..f00902c532cc 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -567,6 +567,8 @@ static int sock_setbindtodevice(struct sock *sk, char __user *optval,
lock_sock(sk);
sk->sk_bound_dev_if = index;
+ if (sk->sk_prot->rehash)
+ sk->sk_prot->rehash(sk);
sk_dst_reset(sk);
release_sock(sk);
@@ -698,6 +700,7 @@ int sock_setsockopt(struct socket *sock, int level, int optname,
break;
case SO_DONTROUTE:
sock_valbool_flag(sk, SOCK_LOCALROUTE, valbool);
+ sk_dst_reset(sk);
break;
case SO_BROADCAST:
sock_valbool_flag(sk, SOCK_BROADCAST, valbool);
@@ -950,10 +953,12 @@ set_rcvbuf:
clear_bit(SOCK_PASSSEC, &sock->flags);
break;
case SO_MARK:
- if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))
+ if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) {
ret = -EPERM;
- else
+ } else if (val != sk->sk_mark) {
sk->sk_mark = val;
+ sk_dst_reset(sk);
+ }
break;
case SO_RXQ_OVFL:
@@ -1014,7 +1019,10 @@ set_rcvbuf:
case SO_ZEROCOPY:
if (sk->sk_family == PF_INET || sk->sk_family == PF_INET6) {
- if (sk->sk_protocol != IPPROTO_TCP)
+ if (!((sk->sk_type == SOCK_STREAM &&
+ sk->sk_protocol == IPPROTO_TCP) ||
+ (sk->sk_type == SOCK_DGRAM &&
+ sk->sk_protocol == IPPROTO_UDP)))
ret = -ENOTSUPP;
} else if (sk->sk_family != PF_RDS) {
ret = -ENOTSUPP;
diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c
index ba5cba56f574..d8fe3e549373 100644
--- a/net/core/sock_reuseport.c
+++ b/net/core/sock_reuseport.c
@@ -187,6 +187,7 @@ int reuseport_add_sock(struct sock *sk, struct sock *sk2, bool bind_inany)
call_rcu(&old_reuse->rcu, reuseport_free_rcu);
return 0;
}
+EXPORT_SYMBOL(reuseport_add_sock);
void reuseport_detach_sock(struct sock *sk)
{
diff --git a/net/core/stream.c b/net/core/stream.c
index 7d329fb1f553..e94bb02a5629 100644
--- a/net/core/stream.c
+++ b/net/core/stream.c
@@ -32,7 +32,7 @@ void sk_stream_write_space(struct sock *sk)
struct socket *sock = sk->sk_socket;
struct socket_wq *wq;
- if (sk_stream_is_writeable(sk) && sock) {
+ if (__sk_stream_is_writeable(sk, 1) && sock) {
clear_bit(SOCK_NOSPACE, &sock->flags);
rcu_read_lock();
generated by cgit v1.2.3 (git 2.39.1) at 2024-11-24 18:34:49 +0000