linux/net/core/dst.c
Linus Torvalds 7e68dd7d07 Networking changes for 6.2.
Core
 ----
  - Allow live renaming when an interface is up
 
  - Add retpoline wrappers for tc, improving considerably the
    performances of complex queue discipline configurations.
 
  - Add inet drop monitor support.
 
  - A few GRO performance improvements.
 
  - Add infrastructure for atomic dev stats, addressing long standing
    data races.
 
  - De-duplicate common code between OVS and conntrack offloading
    infrastructure.
 
  - A bunch of UBSAN_BOUNDS/FORTIFY_SOURCE improvements.
 
  - Netfilter: introduce packet parser for tunneled packets
 
  - Replace IPVS timer-based estimators with kthreads to scale up
    the workload with the number of available CPUs.
 
  - Add the helper support for connection-tracking OVS offload.
 
 BPF
 ---
  - Support for user defined BPF objects: the use case is to allocate
    own objects, build own object hierarchies and use the building
    blocks to build own data structures flexibly, for example, linked
    lists in BPF.
 
  - Make cgroup local storage available to non-cgroup attached BPF
    programs.
 
  - Avoid unnecessary deadlock detection and failures wrt BPF task
    storage helpers.
 
  - A relevant bunch of BPF verifier fixes and improvements.
 
  - Veristat tool improvements to support custom filtering, sorting,
    and replay of results.
 
  - Add LLVM disassembler as default library for dumping JITed code.
 
  - Lots of new BPF documentation for various BPF maps.
 
  - Add bpf_rcu_read_{,un}lock() support for sleepable programs.
 
  - Add RCU grace period chaining to BPF to wait for the completion
    of access from both sleepable and non-sleepable BPF programs.
 
  - Add support storing struct task_struct objects as kptrs in maps.
 
  - Improve helper UAPI by explicitly defining BPF_FUNC_xxx integer
    values.
 
  - Add libbpf *_opts API-variants for bpf_*_get_fd_by_id() functions.
 
 Protocols
 ---------
  - TCP: implement Protective Load Balancing across switch links.
 
  - TCP: allow dynamically disabling TCP-MD5 static key, reverting
    back to fast[er]-path.
 
  - UDP: Introduce optional per-netns hash lookup table.
 
  - IPv6: simplify and cleanup sockets disposal.
 
  - Netlink: support different type policies for each generic
    netlink operation.
 
  - MPTCP: add MSG_FASTOPEN and FastOpen listener side support.
 
  - MPTCP: add netlink notification support for listener sockets
    events.
 
  - SCTP: add VRF support, allowing sctp sockets binding to VRF
    devices.
 
  - Add bridging MAC Authentication Bypass (MAB) support.
 
  - Extensions for Ethernet VPN bridging implementation to better
    support multicast scenarios.
 
  - More work for Wi-Fi 7 support, comprising conversion of all
    the existing drivers to internal TX queue usage.
 
  - IPSec: introduce a new offload type (packet offload) allowing
    complete header processing and crypto offloading.
 
  - IPSec: extended ack support for more descriptive XFRM error
    reporting.
 
  - RXRPC: increase SACK table size and move processing into a
    per-local endpoint kernel thread, reducing considerably the
    required locking.
 
  - IEEE 802154: synchronous send frame and extended filtering
    support, initial support for scanning available 15.4 networks.
 
  - Tun: bump the link speed from 10Mbps to 10Gbps.
 
  - Tun/VirtioNet: implement UDP segmentation offload support.
 
 Driver API
 ----------
 
  - PHY/SFP: improve power level switching between standard
    level 1 and the higher power levels.
 
  - New API for netdev <-> devlink_port linkage.
 
  - PTP: convert existing drivers to new frequency adjustment
    implementation.
 
  - DSA: add support for rx offloading.
 
  - Autoload DSA tagging driver when dynamically changing protocol.
 
  - Add new PCP and APPTRUST attributes to Data Center Bridging.
 
  - Add configuration support for 800Gbps link speed.
 
  - Add devlink port function attribute to enable/disable RoCE and
    migratable.
 
  - Extend devlink-rate to support strict prioriry and weighted fair
    queuing.
 
  - Add devlink support to directly reading from region memory.
 
  - New device tree helper to fetch MAC address from nvmem.
 
  - New big TCP helper to simplify temporary header stripping.
 
 New hardware / drivers
 ----------------------
 
  - Ethernet:
    - Marvel Octeon CNF95N and CN10KB Ethernet Switches.
    - Marvel Prestera AC5X Ethernet Switch.
    - WangXun 10 Gigabit NIC.
    - Motorcomm yt8521 Gigabit Ethernet.
    - Microchip ksz9563 Gigabit Ethernet Switch.
    - Microsoft Azure Network Adapter.
    - Linux Automation 10Base-T1L adapter.
 
  - PHY:
    - Aquantia AQR112 and AQR412.
    - Motorcomm YT8531S.
 
  - PTP:
    - Orolia ART-CARD.
 
  - WiFi:
    - MediaTek Wi-Fi 7 (802.11be) devices.
    - RealTek rtw8821cu, rtw8822bu, rtw8822cu and rtw8723du USB
      devices.
 
  - Bluetooth:
    - Broadcom BCM4377/4378/4387 Bluetooth chipsets.
    - Realtek RTL8852BE and RTL8723DS.
    - Cypress.CYW4373A0 WiFi + Bluetooth combo device.
 
 Drivers
 -------
  - CAN:
    - gs_usb: bus error reporting support.
    - kvaser_usb: listen only and bus error reporting support.
 
  - Ethernet NICs:
    - Intel (100G):
      - extend action skbedit to RX queue mapping.
      - implement devlink-rate support.
      - support direct read from memory.
    - nVidia/Mellanox (mlx5):
      - SW steering improvements, increasing rules update rate.
      - Support for enhanced events compression.
      - extend H/W offload packet manipulation capabilities.
      - implement IPSec packet offload mode.
    - nVidia/Mellanox (mlx4):
      - better big TCP support.
    - Netronome Ethernet NICs (nfp):
      - IPsec offload support.
      - add support for multicast filter.
    - Broadcom:
      - RSS and PTP support improvements.
    - AMD/SolarFlare:
      - netlink extened ack improvements.
      - add basic flower matches to offload, and related stats.
    - Virtual NICs:
      - ibmvnic: introduce affinity hint support.
    - small / embedded:
      - FreeScale fec: add initial XDP support.
      - Marvel mv643xx_eth: support MII/GMII/RGMII modes for Kirkwood.
      - TI am65-cpsw: add suspend/resume support.
      - Mediatek MT7986: add RX wireless wthernet dispatch support.
      - Realtek 8169: enable GRO software interrupt coalescing per
        default.
 
  - Ethernet high-speed switches:
    - Microchip (sparx5):
      - add support for Sparx5 TC/flower H/W offload via VCAP.
    - Mellanox mlxsw:
      - add 802.1X and MAC Authentication Bypass offload support.
      - add ip6gre support.
 
  - Embedded Ethernet switches:
    - Mediatek (mtk_eth_soc):
      - improve PCS implementation, add DSA untag support.
      - enable flow offload support.
    - Renesas:
      - add rswitch R-Car Gen4 gPTP support.
    - Microchip (lan966x):
      - add full XDP support.
      - add TC H/W offload via VCAP.
      - enable PTP on bridge interfaces.
    - Microchip (ksz8):
      - add MTU support for KSZ8 series.
 
  - Qualcomm 802.11ax WiFi (ath11k):
    - support configuring channel dwell time during scan.
 
  - MediaTek WiFi (mt76):
    - enable Wireless Ethernet Dispatch (WED) offload support.
    - add ack signal support.
    - enable coredump support.
    - remain_on_channel support.
 
  - Intel WiFi (iwlwifi):
    - enable Wi-Fi 7 Extremely High Throughput (EHT) PHY capabilities.
    - 320 MHz channels support.
 
  - RealTek WiFi (rtw89):
    - new dynamic header firmware format support.
    - wake-over-WLAN support.
 
 Signed-off-by: Paolo Abeni <pabeni@redhat.com>
 -----BEGIN PGP SIGNATURE-----
 
 iQJGBAABCAAwFiEEg1AjqC77wbdLX2LbKSR5jcyPE6QFAmOYXUcSHHBhYmVuaUBy
 ZWRoYXQuY29tAAoJECkkeY3MjxOk8zQP/R7BZtbJMTPiWkRnSoKHnAyupDVwrz5U
 ktukLkwPsCyJuEbAjgxrxf4EEEQ9uq2FFlxNSYuKiiQMqIpFxV6KED7LCUygn4Tc
 kxtkp0Q+5XiqisWlQmtfExf2OjuuPqcjV9tWCDBI6GebKUbfNwY/eI44RcMu4BSv
 DzIlW5GkX/kZAPqnnuqaLsN3FudDTJHGEAD7NbA++7wJ076RWYSLXlFv0Z+SCSPS
 H8/PEG0/ZK/65rIWMAFRClJ9BNIDwGVgp0GrsIvs1gqbRUOlA1hl1rDM21TqtNFf
 5QPQT7sIfTcCE/nerxKJD5JE3JyP+XRlRn96PaRw3rt4MgI6I/EOj/HOKQ5tMCNc
 oPiqb7N70+hkLZyr42qX+vN9eDPjp2koEQm7EO2Zs+/534/zWDs24Zfk/Aa1ps0I
 Fa82oGjAgkBhGe/FZ6i5cYoLcyxqRqZV1Ws9XQMl72qRC7/BwvNbIW6beLpCRyeM
 yYIU+0e9dEm+wHQEdh2niJuVtR63hy8tvmPx56lyh+6u0+pondkwbfSiC5aD3kAC
 ikKsN5DyEsdXyiBAlytCEBxnaOjQy4RAz+3YXSiS0eBNacXp03UUrNGx4Pzpu/D0
 QLFJhBnMFFCgy5to8/DvKnrTPgZdSURwqbIUcZdvU21f1HLR8tUTpaQnYffc/Whm
 V8gnt1EL+0cc
 =CbJC
 -----END PGP SIGNATURE-----

Merge tag 'net-next-6.2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from Paolo Abeni:
 "Core:

   - Allow live renaming when an interface is up

   - Add retpoline wrappers for tc, improving considerably the
     performances of complex queue discipline configurations

   - Add inet drop monitor support

   - A few GRO performance improvements

   - Add infrastructure for atomic dev stats, addressing long standing
     data races

   - De-duplicate common code between OVS and conntrack offloading
     infrastructure

   - A bunch of UBSAN_BOUNDS/FORTIFY_SOURCE improvements

   - Netfilter: introduce packet parser for tunneled packets

   - Replace IPVS timer-based estimators with kthreads to scale up the
     workload with the number of available CPUs

   - Add the helper support for connection-tracking OVS offload

  BPF:

   - Support for user defined BPF objects: the use case is to allocate
     own objects, build own object hierarchies and use the building
     blocks to build own data structures flexibly, for example, linked
     lists in BPF

   - Make cgroup local storage available to non-cgroup attached BPF
     programs

   - Avoid unnecessary deadlock detection and failures wrt BPF task
     storage helpers

   - A relevant bunch of BPF verifier fixes and improvements

   - Veristat tool improvements to support custom filtering, sorting,
     and replay of results

   - Add LLVM disassembler as default library for dumping JITed code

   - Lots of new BPF documentation for various BPF maps

   - Add bpf_rcu_read_{,un}lock() support for sleepable programs

   - Add RCU grace period chaining to BPF to wait for the completion of
     access from both sleepable and non-sleepable BPF programs

   - Add support storing struct task_struct objects as kptrs in maps

   - Improve helper UAPI by explicitly defining BPF_FUNC_xxx integer
     values

   - Add libbpf *_opts API-variants for bpf_*_get_fd_by_id() functions

  Protocols:

   - TCP: implement Protective Load Balancing across switch links

   - TCP: allow dynamically disabling TCP-MD5 static key, reverting back
     to fast[er]-path

   - UDP: Introduce optional per-netns hash lookup table

   - IPv6: simplify and cleanup sockets disposal

   - Netlink: support different type policies for each generic netlink
     operation

   - MPTCP: add MSG_FASTOPEN and FastOpen listener side support

   - MPTCP: add netlink notification support for listener sockets events

   - SCTP: add VRF support, allowing sctp sockets binding to VRF devices

   - Add bridging MAC Authentication Bypass (MAB) support

   - Extensions for Ethernet VPN bridging implementation to better
     support multicast scenarios

   - More work for Wi-Fi 7 support, comprising conversion of all the
     existing drivers to internal TX queue usage

   - IPSec: introduce a new offload type (packet offload) allowing
     complete header processing and crypto offloading

   - IPSec: extended ack support for more descriptive XFRM error
     reporting

   - RXRPC: increase SACK table size and move processing into a
     per-local endpoint kernel thread, reducing considerably the
     required locking

   - IEEE 802154: synchronous send frame and extended filtering support,
     initial support for scanning available 15.4 networks

   - Tun: bump the link speed from 10Mbps to 10Gbps

   - Tun/VirtioNet: implement UDP segmentation offload support

  Driver API:

   - PHY/SFP: improve power level switching between standard level 1 and
     the higher power levels

   - New API for netdev <-> devlink_port linkage

   - PTP: convert existing drivers to new frequency adjustment
     implementation

   - DSA: add support for rx offloading

   - Autoload DSA tagging driver when dynamically changing protocol

   - Add new PCP and APPTRUST attributes to Data Center Bridging

   - Add configuration support for 800Gbps link speed

   - Add devlink port function attribute to enable/disable RoCE and
     migratable

   - Extend devlink-rate to support strict prioriry and weighted fair
     queuing

   - Add devlink support to directly reading from region memory

   - New device tree helper to fetch MAC address from nvmem

   - New big TCP helper to simplify temporary header stripping

  New hardware / drivers:

   - Ethernet:
      - Marvel Octeon CNF95N and CN10KB Ethernet Switches
      - Marvel Prestera AC5X Ethernet Switch
      - WangXun 10 Gigabit NIC
      - Motorcomm yt8521 Gigabit Ethernet
      - Microchip ksz9563 Gigabit Ethernet Switch
      - Microsoft Azure Network Adapter
      - Linux Automation 10Base-T1L adapter

   - PHY:
      - Aquantia AQR112 and AQR412
      - Motorcomm YT8531S

   - PTP:
      - Orolia ART-CARD

   - WiFi:
      - MediaTek Wi-Fi 7 (802.11be) devices
      - RealTek rtw8821cu, rtw8822bu, rtw8822cu and rtw8723du USB
        devices

   - Bluetooth:
      - Broadcom BCM4377/4378/4387 Bluetooth chipsets
      - Realtek RTL8852BE and RTL8723DS
      - Cypress.CYW4373A0 WiFi + Bluetooth combo device

  Drivers:

   - CAN:
      - gs_usb: bus error reporting support
      - kvaser_usb: listen only and bus error reporting support

   - Ethernet NICs:
      - Intel (100G):
         - extend action skbedit to RX queue mapping
         - implement devlink-rate support
         - support direct read from memory
      - nVidia/Mellanox (mlx5):
         - SW steering improvements, increasing rules update rate
         - Support for enhanced events compression
         - extend H/W offload packet manipulation capabilities
         - implement IPSec packet offload mode
      - nVidia/Mellanox (mlx4):
         - better big TCP support
      - Netronome Ethernet NICs (nfp):
         - IPsec offload support
         - add support for multicast filter
      - Broadcom:
         - RSS and PTP support improvements
      - AMD/SolarFlare:
         - netlink extened ack improvements
         - add basic flower matches to offload, and related stats
      - Virtual NICs:
         - ibmvnic: introduce affinity hint support
      - small / embedded:
         - FreeScale fec: add initial XDP support
         - Marvel mv643xx_eth: support MII/GMII/RGMII modes for Kirkwood
         - TI am65-cpsw: add suspend/resume support
         - Mediatek MT7986: add RX wireless wthernet dispatch support
         - Realtek 8169: enable GRO software interrupt coalescing per
           default

   - Ethernet high-speed switches:
      - Microchip (sparx5):
         - add support for Sparx5 TC/flower H/W offload via VCAP
      - Mellanox mlxsw:
         - add 802.1X and MAC Authentication Bypass offload support
         - add ip6gre support

   - Embedded Ethernet switches:
      - Mediatek (mtk_eth_soc):
         - improve PCS implementation, add DSA untag support
         - enable flow offload support
      - Renesas:
         - add rswitch R-Car Gen4 gPTP support
      - Microchip (lan966x):
         - add full XDP support
         - add TC H/W offload via VCAP
         - enable PTP on bridge interfaces
      - Microchip (ksz8):
         - add MTU support for KSZ8 series

   - Qualcomm 802.11ax WiFi (ath11k):
      - support configuring channel dwell time during scan

   - MediaTek WiFi (mt76):
      - enable Wireless Ethernet Dispatch (WED) offload support
      - add ack signal support
      - enable coredump support
      - remain_on_channel support

   - Intel WiFi (iwlwifi):
      - enable Wi-Fi 7 Extremely High Throughput (EHT) PHY capabilities
      - 320 MHz channels support

   - RealTek WiFi (rtw89):
      - new dynamic header firmware format support
      - wake-over-WLAN support"

* tag 'net-next-6.2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2002 commits)
  ipvs: fix type warning in do_div() on 32 bit
  net: lan966x: Remove a useless test in lan966x_ptp_add_trap()
  net: ipa: add IPA v4.7 support
  dt-bindings: net: qcom,ipa: Add SM6350 compatible
  bnxt: Use generic HBH removal helper in tx path
  IPv6/GRO: generic helper to remove temporary HBH/jumbo header in driver
  selftests: forwarding: Add bridge MDB test
  selftests: forwarding: Rename bridge_mdb test
  bridge: mcast: Support replacement of MDB port group entries
  bridge: mcast: Allow user space to specify MDB entry routing protocol
  bridge: mcast: Allow user space to add (*, G) with a source list and filter mode
  bridge: mcast: Add support for (*, G) with a source list and filter mode
  bridge: mcast: Avoid arming group timer when (S, G) corresponds to a source
  bridge: mcast: Add a flag for user installed source entries
  bridge: mcast: Expose __br_multicast_del_group_src()
  bridge: mcast: Expose br_multicast_new_group_src()
  bridge: mcast: Add a centralized error path
  bridge: mcast: Place netlink policy before validation functions
  bridge: mcast: Split (*, G) and (S, G) addition into different functions
  bridge: mcast: Do not derive entry type from its filter mode
  ...
2022-12-13 15:47:48 -08:00

360 lines
8.9 KiB
C

// SPDX-License-Identifier: GPL-2.0-only
/*
* net/core/dst.c Protocol independent destination cache.
*
* Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
*
*/
#include <linux/bitops.h>
#include <linux/errno.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/workqueue.h>
#include <linux/mm.h>
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/netdevice.h>
#include <linux/skbuff.h>
#include <linux/string.h>
#include <linux/types.h>
#include <net/net_namespace.h>
#include <linux/sched.h>
#include <linux/prefetch.h>
#include <net/lwtunnel.h>
#include <net/xfrm.h>
#include <net/dst.h>
#include <net/dst_metadata.h>
int dst_discard_out(struct net *net, struct sock *sk, struct sk_buff *skb)
{
kfree_skb(skb);
return 0;
}
EXPORT_SYMBOL(dst_discard_out);
const struct dst_metrics dst_default_metrics = {
/* This initializer is needed to force linker to place this variable
* into const section. Otherwise it might end into bss section.
* We really want to avoid false sharing on this variable, and catch
* any writes on it.
*/
.refcnt = REFCOUNT_INIT(1),
};
EXPORT_SYMBOL(dst_default_metrics);
void dst_init(struct dst_entry *dst, struct dst_ops *ops,
struct net_device *dev, int initial_ref, int initial_obsolete,
unsigned short flags)
{
dst->dev = dev;
netdev_hold(dev, &dst->dev_tracker, GFP_ATOMIC);
dst->ops = ops;
dst_init_metrics(dst, dst_default_metrics.metrics, true);
dst->expires = 0UL;
#ifdef CONFIG_XFRM
dst->xfrm = NULL;
#endif
dst->input = dst_discard;
dst->output = dst_discard_out;
dst->error = 0;
dst->obsolete = initial_obsolete;
dst->header_len = 0;
dst->trailer_len = 0;
#ifdef CONFIG_IP_ROUTE_CLASSID
dst->tclassid = 0;
#endif
dst->lwtstate = NULL;
atomic_set(&dst->__refcnt, initial_ref);
dst->__use = 0;
dst->lastuse = jiffies;
dst->flags = flags;
if (!(flags & DST_NOCOUNT))
dst_entries_add(ops, 1);
}
EXPORT_SYMBOL(dst_init);
void *dst_alloc(struct dst_ops *ops, struct net_device *dev,
int initial_ref, int initial_obsolete, unsigned short flags)
{
struct dst_entry *dst;
if (ops->gc &&
!(flags & DST_NOCOUNT) &&
dst_entries_get_fast(ops) > ops->gc_thresh) {
if (ops->gc(ops)) {
pr_notice_ratelimited("Route cache is full: consider increasing sysctl net.ipv6.route.max_size.\n");
return NULL;
}
}
dst = kmem_cache_alloc(ops->kmem_cachep, GFP_ATOMIC);
if (!dst)
return NULL;
dst_init(dst, ops, dev, initial_ref, initial_obsolete, flags);
return dst;
}
EXPORT_SYMBOL(dst_alloc);
struct dst_entry *dst_destroy(struct dst_entry * dst)
{
struct dst_entry *child = NULL;
smp_rmb();
#ifdef CONFIG_XFRM
if (dst->xfrm) {
struct xfrm_dst *xdst = (struct xfrm_dst *) dst;
child = xdst->child;
}
#endif
if (!(dst->flags & DST_NOCOUNT))
dst_entries_add(dst->ops, -1);
if (dst->ops->destroy)
dst->ops->destroy(dst);
netdev_put(dst->dev, &dst->dev_tracker);
lwtstate_put(dst->lwtstate);
if (dst->flags & DST_METADATA)
metadata_dst_free((struct metadata_dst *)dst);
else
kmem_cache_free(dst->ops->kmem_cachep, dst);
dst = child;
if (dst)
dst_release_immediate(dst);
return NULL;
}
EXPORT_SYMBOL(dst_destroy);
static void dst_destroy_rcu(struct rcu_head *head)
{
struct dst_entry *dst = container_of(head, struct dst_entry, rcu_head);
dst = dst_destroy(dst);
}
/* Operations to mark dst as DEAD and clean up the net device referenced
* by dst:
* 1. put the dst under blackhole interface and discard all tx/rx packets
* on this route.
* 2. release the net_device
* This function should be called when removing routes from the fib tree
* in preparation for a NETDEV_DOWN/NETDEV_UNREGISTER event and also to
* make the next dst_ops->check() fail.
*/
void dst_dev_put(struct dst_entry *dst)
{
struct net_device *dev = dst->dev;
dst->obsolete = DST_OBSOLETE_DEAD;
if (dst->ops->ifdown)
dst->ops->ifdown(dst, dev, true);
dst->input = dst_discard;
dst->output = dst_discard_out;
dst->dev = blackhole_netdev;
netdev_ref_replace(dev, blackhole_netdev, &dst->dev_tracker,
GFP_ATOMIC);
}
EXPORT_SYMBOL(dst_dev_put);
void dst_release(struct dst_entry *dst)
{
if (dst) {
int newrefcnt;
newrefcnt = atomic_dec_return(&dst->__refcnt);
if (WARN_ONCE(newrefcnt < 0, "dst_release underflow"))
net_warn_ratelimited("%s: dst:%p refcnt:%d\n",
__func__, dst, newrefcnt);
if (!newrefcnt)
call_rcu_hurry(&dst->rcu_head, dst_destroy_rcu);
}
}
EXPORT_SYMBOL(dst_release);
void dst_release_immediate(struct dst_entry *dst)
{
if (dst) {
int newrefcnt;
newrefcnt = atomic_dec_return(&dst->__refcnt);
if (WARN_ONCE(newrefcnt < 0, "dst_release_immediate underflow"))
net_warn_ratelimited("%s: dst:%p refcnt:%d\n",
__func__, dst, newrefcnt);
if (!newrefcnt)
dst_destroy(dst);
}
}
EXPORT_SYMBOL(dst_release_immediate);
u32 *dst_cow_metrics_generic(struct dst_entry *dst, unsigned long old)
{
struct dst_metrics *p = kmalloc(sizeof(*p), GFP_ATOMIC);
if (p) {
struct dst_metrics *old_p = (struct dst_metrics *)__DST_METRICS_PTR(old);
unsigned long prev, new;
refcount_set(&p->refcnt, 1);
memcpy(p->metrics, old_p->metrics, sizeof(p->metrics));
new = (unsigned long) p;
prev = cmpxchg(&dst->_metrics, old, new);
if (prev != old) {
kfree(p);
p = (struct dst_metrics *)__DST_METRICS_PTR(prev);
if (prev & DST_METRICS_READ_ONLY)
p = NULL;
} else if (prev & DST_METRICS_REFCOUNTED) {
if (refcount_dec_and_test(&old_p->refcnt))
kfree(old_p);
}
}
BUILD_BUG_ON(offsetof(struct dst_metrics, metrics) != 0);
return (u32 *)p;
}
EXPORT_SYMBOL(dst_cow_metrics_generic);
/* Caller asserts that dst_metrics_read_only(dst) is false. */
void __dst_destroy_metrics_generic(struct dst_entry *dst, unsigned long old)
{
unsigned long prev, new;
new = ((unsigned long) &dst_default_metrics) | DST_METRICS_READ_ONLY;
prev = cmpxchg(&dst->_metrics, old, new);
if (prev == old)
kfree(__DST_METRICS_PTR(old));
}
EXPORT_SYMBOL(__dst_destroy_metrics_generic);
struct dst_entry *dst_blackhole_check(struct dst_entry *dst, u32 cookie)
{
return NULL;
}
u32 *dst_blackhole_cow_metrics(struct dst_entry *dst, unsigned long old)
{
return NULL;
}
struct neighbour *dst_blackhole_neigh_lookup(const struct dst_entry *dst,
struct sk_buff *skb,
const void *daddr)
{
return NULL;
}
void dst_blackhole_update_pmtu(struct dst_entry *dst, struct sock *sk,
struct sk_buff *skb, u32 mtu,
bool confirm_neigh)
{
}
EXPORT_SYMBOL_GPL(dst_blackhole_update_pmtu);
void dst_blackhole_redirect(struct dst_entry *dst, struct sock *sk,
struct sk_buff *skb)
{
}
EXPORT_SYMBOL_GPL(dst_blackhole_redirect);
unsigned int dst_blackhole_mtu(const struct dst_entry *dst)
{
unsigned int mtu = dst_metric_raw(dst, RTAX_MTU);
return mtu ? : dst->dev->mtu;
}
EXPORT_SYMBOL_GPL(dst_blackhole_mtu);
static struct dst_ops dst_blackhole_ops = {
.family = AF_UNSPEC,
.neigh_lookup = dst_blackhole_neigh_lookup,
.check = dst_blackhole_check,
.cow_metrics = dst_blackhole_cow_metrics,
.update_pmtu = dst_blackhole_update_pmtu,
.redirect = dst_blackhole_redirect,
.mtu = dst_blackhole_mtu,
};
static void __metadata_dst_init(struct metadata_dst *md_dst,
enum metadata_type type, u8 optslen)
{
struct dst_entry *dst;
dst = &md_dst->dst;
dst_init(dst, &dst_blackhole_ops, NULL, 1, DST_OBSOLETE_NONE,
DST_METADATA | DST_NOCOUNT);
memset(dst + 1, 0, sizeof(*md_dst) + optslen - sizeof(*dst));
md_dst->type = type;
}
struct metadata_dst *metadata_dst_alloc(u8 optslen, enum metadata_type type,
gfp_t flags)
{
struct metadata_dst *md_dst;
md_dst = kmalloc(sizeof(*md_dst) + optslen, flags);
if (!md_dst)
return NULL;
__metadata_dst_init(md_dst, type, optslen);
return md_dst;
}
EXPORT_SYMBOL_GPL(metadata_dst_alloc);
void metadata_dst_free(struct metadata_dst *md_dst)
{
#ifdef CONFIG_DST_CACHE
if (md_dst->type == METADATA_IP_TUNNEL)
dst_cache_destroy(&md_dst->u.tun_info.dst_cache);
#endif
if (md_dst->type == METADATA_XFRM)
dst_release(md_dst->u.xfrm_info.dst_orig);
kfree(md_dst);
}
EXPORT_SYMBOL_GPL(metadata_dst_free);
struct metadata_dst __percpu *
metadata_dst_alloc_percpu(u8 optslen, enum metadata_type type, gfp_t flags)
{
int cpu;
struct metadata_dst __percpu *md_dst;
md_dst = __alloc_percpu_gfp(sizeof(struct metadata_dst) + optslen,
__alignof__(struct metadata_dst), flags);
if (!md_dst)
return NULL;
for_each_possible_cpu(cpu)
__metadata_dst_init(per_cpu_ptr(md_dst, cpu), type, optslen);
return md_dst;
}
EXPORT_SYMBOL_GPL(metadata_dst_alloc_percpu);
void metadata_dst_free_percpu(struct metadata_dst __percpu *md_dst)
{
int cpu;
for_each_possible_cpu(cpu) {
struct metadata_dst *one_md_dst = per_cpu_ptr(md_dst, cpu);
#ifdef CONFIG_DST_CACHE
if (one_md_dst->type == METADATA_IP_TUNNEL)
dst_cache_destroy(&one_md_dst->u.tun_info.dst_cache);
#endif
if (one_md_dst->type == METADATA_XFRM)
dst_release(one_md_dst->u.xfrm_info.dst_orig);
}
free_percpu(md_dst);
}
EXPORT_SYMBOL_GPL(metadata_dst_free_percpu);