diff options
author | Linus Torvalds | 2022-08-03 16:29:08 -0700 |
---|---|---|
committer | Linus Torvalds | 2022-08-03 16:29:08 -0700 |
commit | f86d1fbbe7858884d6754534a0afbb74fc30bc26 (patch) | |
tree | f61796870edefbe77d495e9d719c68af1d14275b /net/ipv6 | |
parent | 526942b8134cc34d25d27f95dfff98b8ce2f6fcd (diff) | |
parent | 7c6327c77d509e78bff76f2a4551fcfee851682e (diff) |
Merge tag 'net-next-6.0' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next
Pull networking changes from Paolo Abeni:
"Core:
- Refactor the forward memory allocation to better cope with memory
pressure with many open sockets, moving from a per socket cache to
a per-CPU one
- Replace rwlocks with RCU for better fairness in ping, raw sockets
and IP multicast router.
- Network-side support for IO uring zero-copy send.
- A few skb drop reason improvements, including codegen the source
file with string mapping instead of using macro magic.
- Rename reference tracking helpers to a more consistent netdev_*
schema.
- Adapt u64_stats_t type to address load/store tearing issues.
- Refine debug helper usage to reduce the log noise caused by bots.
BPF:
- Improve socket map performance, avoiding skb cloning on read
operation.
- Add support for 64 bits enum, to match types exposed by kernel.
- Introduce support for sleepable uprobes program.
- Introduce support for enum textual representation in libbpf.
- New helpers to implement synproxy with eBPF/XDP.
- Improve loop performances, inlining indirect calls when possible.
- Removed all the deprecated libbpf APIs.
- Implement new eBPF-based LSM flavor.
- Add type match support, which allow accurate queries to the eBPF
used types.
- A few TCP congetsion control framework usability improvements.
- Add new infrastructure to manipulate CT entries via eBPF programs.
- Allow for livepatch (KLP) and BPF trampolines to attach to the same
kernel function.
Protocols:
- Introduce per network namespace lookup tables for unix sockets,
increasing scalability and reducing contention.
- Preparation work for Wi-Fi 7 Multi-Link Operation (MLO) support.
- Add support to forciby close TIME_WAIT TCP sockets via user-space
tools.
- Significant performance improvement for the TLS 1.3 receive path,
both for zero-copy and not-zero-copy.
- Support for changing the initial MTPCP subflow priority/backup
status
- Introduce virtually contingus buffers for sockets over RDMA, to
cope better with memory pressure.
- Extend CAN ethtool support with timestamping capabilities
- Refactor CAN build infrastructure to allow building only the needed
features.
Driver API:
- Remove devlink mutex to allow parallel commands on multiple links.
- Add support for pause stats in distributed switch.
- Implement devlink helpers to query and flash line cards.
- New helper for phy mode to register conversion.
New hardware / drivers:
- Ethernet DSA driver for the rockchip mt7531 on BPI-R2 Pro.
- Ethernet DSA driver for the Renesas RZ/N1 A5PSW switch.
- Ethernet DSA driver for the Microchip LAN937x switch.
- Ethernet PHY driver for the Aquantia AQR113C EPHY.
- CAN driver for the OBD-II ELM327 interface.
- CAN driver for RZ/N1 SJA1000 CAN controller.
- Bluetooth: Infineon CYW55572 Wi-Fi plus Bluetooth combo device.
Drivers:
- Intel Ethernet NICs:
- i40e: add support for vlan pruning
- i40e: add support for XDP framented packets
- ice: improved vlan offload support
- ice: add support for PPPoE offload
- Mellanox Ethernet (mlx5)
- refactor packet steering offload for performance and scalability
- extend support for TC offload
- refactor devlink code to clean-up the locking schema
- support stacked vlans for bridge offloads
- use TLS objects pool to improve connection rate
- Netronome Ethernet NICs (nfp):
- extend support for IPv6 fields mangling offload
- add support for vepa mode in HW bridge
- better support for virtio data path acceleration (VDPA)
- enable TSO by default
- Microsoft vNIC driver (mana)
- add support for XDP redirect
- Others Ethernet drivers:
- bonding: add per-port priority support
- microchip lan743x: extend phy support
- Fungible funeth: support UDP segmentation offload and XDP xmit
- Solarflare EF100: add support for virtual function representors
- MediaTek SoC: add XDP support
- Mellanox Ethernet/IB switch (mlxsw):
- dropped support for unreleased H/W (XM router).
- improved stats accuracy
- unified bridge model coversion improving scalability (parts 1-6)
- support for PTP in Spectrum-2 asics
- Broadcom PHYs
- add PTP support for BCM54210E
- add support for the BCM53128 internal PHY
- Marvell Ethernet switches (prestera):
- implement support for multicast forwarding offload
- Embedded Ethernet switches:
- refactor OcteonTx MAC filter for better scalability
- improve TC H/W offload for the Felix driver
- refactor the Microchip ksz8 and ksz9477 drivers to share the
probe code (parts 1, 2), add support for phylink mac
configuration
- Other WiFi:
- Microchip wilc1000: diable WEP support and enable WPA3
- Atheros ath10k: encapsulation offload support
Old code removal:
- Neterion vxge ethernet driver: this is untouched since more than 10 years"
* tag 'net-next-6.0' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1890 commits)
doc: sfp-phylink: Fix a broken reference
wireguard: selftests: support UML
wireguard: allowedips: don't corrupt stack when detecting overflow
wireguard: selftests: update config fragments
wireguard: ratelimiter: use hrtimer in selftest
net/mlx5e: xsk: Discard unaligned XSK frames on striding RQ
net: usb: ax88179_178a: Bind only to vendor-specific interface
selftests: net: fix IOAM test skip return code
net: usb: make USB_RTL8153_ECM non user configurable
net: marvell: prestera: remove reduntant code
octeontx2-pf: Reduce minimum mtu size to 60
net: devlink: Fix missing mutex_unlock() call
net/tls: Remove redundant workqueue flush before destroy
net: txgbe: Fix an error handling path in txgbe_probe()
net: dsa: Fix spelling mistakes and cleanup code
Documentation: devlink: add add devlink-selftests to the table of contents
dccp: put dccp_qpolicy_full() and dccp_qpolicy_push() in the same lock
net: ionic: fix error check for vlan flags in ionic_set_nic_features()
net: ice: fix error NETIF_F_HW_VLAN_CTAG_FILTER check in ice_vsi_sync_fltr()
nfp: flower: add support for tunnel offload without key ID
...
Diffstat (limited to 'net/ipv6')
-rw-r--r-- | net/ipv6/addrconf.c | 70 | ||||
-rw-r--r-- | net/ipv6/addrconf_core.c | 2 | ||||
-rw-r--r-- | net/ipv6/af_inet6.c | 6 | ||||
-rw-r--r-- | net/ipv6/esp6.c | 4 | ||||
-rw-r--r-- | net/ipv6/ip6_gre.c | 51 | ||||
-rw-r--r-- | net/ipv6/ip6_tunnel.c | 22 | ||||
-rw-r--r-- | net/ipv6/ip6_vti.c | 4 | ||||
-rw-r--r-- | net/ipv6/ip6mr.c | 301 | ||||
-rw-r--r-- | net/ipv6/ndisc.c | 30 | ||||
-rw-r--r-- | net/ipv6/ping.c | 6 | ||||
-rw-r--r-- | net/ipv6/raw.c | 120 | ||||
-rw-r--r-- | net/ipv6/route.c | 12 | ||||
-rw-r--r-- | net/ipv6/seg6_iptunnel.c | 140 | ||||
-rw-r--r-- | net/ipv6/sit.c | 12 | ||||
-rw-r--r-- | net/ipv6/tcp_ipv6.c | 8 | ||||
-rw-r--r-- | net/ipv6/udp.c | 3 | ||||
-rw-r--r-- | net/ipv6/udplite.c | 3 | ||||
-rw-r--r-- | net/ipv6/xfrm6_policy.c | 4 |
18 files changed, 527 insertions, 271 deletions
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 49cc6587dd77..b624e3d8c5f0 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -398,13 +398,13 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev) if (ndev->cnf.forwarding) dev_disable_lro(dev); /* We refer to the device */ - dev_hold_track(dev, &ndev->dev_tracker, GFP_KERNEL); + netdev_hold(dev, &ndev->dev_tracker, GFP_KERNEL); if (snmp6_alloc_dev(ndev) < 0) { netdev_dbg(dev, "%s: cannot allocate memory for statistics\n", __func__); neigh_parms_release(&nd_tbl, ndev->nd_parms); - dev_put_track(dev, &ndev->dev_tracker); + netdev_put(dev, &ndev->dev_tracker); kfree(ndev); return ERR_PTR(err); } @@ -4520,6 +4520,39 @@ restart: /* We try to batch several events at once. */ age = (now - ifp->tstamp + ADDRCONF_TIMER_FUZZ_MINUS) / HZ; + if ((ifp->flags&IFA_F_TEMPORARY) && + !(ifp->flags&IFA_F_TENTATIVE) && + ifp->prefered_lft != INFINITY_LIFE_TIME && + !ifp->regen_count && ifp->ifpub) { + /* This is a non-regenerated temporary addr. */ + + unsigned long regen_advance = ifp->idev->cnf.regen_max_retry * + ifp->idev->cnf.dad_transmits * + max(NEIGH_VAR(ifp->idev->nd_parms, RETRANS_TIME), HZ/100) / HZ; + + if (age + regen_advance >= ifp->prefered_lft) { + struct inet6_ifaddr *ifpub = ifp->ifpub; + if (time_before(ifp->tstamp + ifp->prefered_lft * HZ, next)) + next = ifp->tstamp + ifp->prefered_lft * HZ; + + ifp->regen_count++; + in6_ifa_hold(ifp); + in6_ifa_hold(ifpub); + spin_unlock(&ifp->lock); + + spin_lock(&ifpub->lock); + ifpub->regen_count = 0; + spin_unlock(&ifpub->lock); + rcu_read_unlock_bh(); + ipv6_create_tempaddr(ifpub, true); + in6_ifa_put(ifpub); + in6_ifa_put(ifp); + rcu_read_lock_bh(); + goto restart; + } else if (time_before(ifp->tstamp + ifp->prefered_lft * HZ - regen_advance * HZ, next)) + next = ifp->tstamp + ifp->prefered_lft * HZ - regen_advance * HZ; + } + if (ifp->valid_lft != INFINITY_LIFE_TIME && age >= ifp->valid_lft) { spin_unlock(&ifp->lock); @@ -4553,35 +4586,6 @@ restart: in6_ifa_put(ifp); goto restart; } - } else if ((ifp->flags&IFA_F_TEMPORARY) && - !(ifp->flags&IFA_F_TENTATIVE)) { - unsigned long regen_advance = ifp->idev->cnf.regen_max_retry * - ifp->idev->cnf.dad_transmits * - max(NEIGH_VAR(ifp->idev->nd_parms, RETRANS_TIME), HZ/100) / HZ; - - if (age >= ifp->prefered_lft - regen_advance) { - struct inet6_ifaddr *ifpub = ifp->ifpub; - if (time_before(ifp->tstamp + ifp->prefered_lft * HZ, next)) - next = ifp->tstamp + ifp->prefered_lft * HZ; - if (!ifp->regen_count && ifpub) { - ifp->regen_count++; - in6_ifa_hold(ifp); - in6_ifa_hold(ifpub); - spin_unlock(&ifp->lock); - - spin_lock(&ifpub->lock); - ifpub->regen_count = 0; - spin_unlock(&ifpub->lock); - rcu_read_unlock_bh(); - ipv6_create_tempaddr(ifpub, true); - in6_ifa_put(ifpub); - in6_ifa_put(ifp); - rcu_read_lock_bh(); - goto restart; - } - } else if (time_before(ifp->tstamp + ifp->prefered_lft * HZ - regen_advance * HZ, next)) - next = ifp->tstamp + ifp->prefered_lft * HZ - regen_advance * HZ; - spin_unlock(&ifp->lock); } else { /* ifp->prefered_lft <= ifp->valid_lft */ if (time_before(ifp->tstamp + ifp->prefered_lft * HZ, next)) @@ -7039,8 +7043,8 @@ static const struct ctl_table addrconf_sysctl[] = { .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = (void *)SYSCTL_ZERO, - .extra2 = (void *)SYSCTL_ONE, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_TWO, }, { /* sentinel */ diff --git a/net/ipv6/addrconf_core.c b/net/ipv6/addrconf_core.c index 881d1477d24a..507a8353a6bd 100644 --- a/net/ipv6/addrconf_core.c +++ b/net/ipv6/addrconf_core.c @@ -263,7 +263,7 @@ void in6_dev_finish_destroy(struct inet6_dev *idev) #ifdef NET_REFCNT_DEBUG pr_debug("%s: %s\n", __func__, dev ? dev->name : "NIL"); #endif - dev_put_track(dev, &idev->dev_tracker); + netdev_put(dev, &idev->dev_tracker); if (!idev->dead) { pr_warn("Freeing alive inet6 device %p\n", idev); return; diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 6f354f8be2c5..2ce0c44d0081 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -63,6 +63,7 @@ #include <net/compat.h> #include <net/xfrm.h> #include <net/ioam6.h> +#include <net/rawv6.h> #include <linux/uaccess.h> #include <linux/mroute6.h> @@ -701,6 +702,7 @@ const struct proto_ops inet6_stream_ops = { .sendpage_locked = tcp_sendpage_locked, .splice_read = tcp_splice_read, .read_sock = tcp_read_sock, + .read_skb = tcp_read_skb, .peek_len = tcp_peek_len, #ifdef CONFIG_COMPAT .compat_ioctl = inet6_compat_ioctl, @@ -726,7 +728,7 @@ const struct proto_ops inet6_dgram_ops = { .getsockopt = sock_common_getsockopt, /* ok */ .sendmsg = inet6_sendmsg, /* retpoline's sake */ .recvmsg = inet6_recvmsg, /* retpoline's sake */ - .read_sock = udp_read_sock, + .read_skb = udp_read_skb, .mmap = sock_no_mmap, .sendpage = sock_no_sendpage, .set_peek_off = sk_set_peek_off, @@ -1073,6 +1075,8 @@ static int __init inet6_init(void) goto out; } + raw_hashinfo_init(&raw_v6_hashinfo); + err = proto_register(&tcpv6_prot, 1); if (err) goto out; diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index 36e1d0f8dd06..8220923a12f7 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -343,7 +343,7 @@ static struct ip_esp_hdr *esp_output_set_esn(struct sk_buff *skb, struct esp_output_extra *extra) { /* For ESN we move the header forward by 4 bytes to - * accomodate the high bits. We will move it back after + * accommodate the high bits. We will move it back after * encryption. */ if ((x->props.flags & XFRM_STATE_ESN)) { @@ -896,7 +896,7 @@ static void esp_input_set_header(struct sk_buff *skb, __be32 *seqhi) struct xfrm_state *x = xfrm_input_state(skb); /* For ESN we move the header forward by 4 bytes to - * accomodate the high bits. We will move it back after + * accommodate the high bits. We will move it back after * decryption. */ if ((x->props.flags & XFRM_STATE_ESN)) { diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index a9051df0625d..80cb50d459e4 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -398,7 +398,7 @@ static void ip6erspan_tunnel_uninit(struct net_device *dev) ip6erspan_tunnel_unlink_md(ign, t); ip6gre_tunnel_unlink(ign, t); dst_cache_reset(&t->dst_cache); - dev_put_track(dev, &t->dev_tracker); + netdev_put(dev, &t->dev_tracker); } static void ip6gre_tunnel_uninit(struct net_device *dev) @@ -411,7 +411,7 @@ static void ip6gre_tunnel_uninit(struct net_device *dev) if (ign->fb_tunnel_dev == dev) WRITE_ONCE(ign->fb_tunnel_dev, NULL); dst_cache_reset(&t->dst_cache); - dev_put_track(dev, &t->dev_tracker); + netdev_put(dev, &t->dev_tracker); } @@ -701,6 +701,33 @@ static int prepare_ip6gre_xmit_ipv6(struct sk_buff *skb, return 0; } +static int prepare_ip6gre_xmit_other(struct sk_buff *skb, + struct net_device *dev, + struct flowi6 *fl6, __u8 *dsfield, + int *encap_limit) +{ + struct ip6_tnl *t = netdev_priv(dev); + + if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) + *encap_limit = t->parms.encap_limit; + + memcpy(fl6, &t->fl.u.ip6, sizeof(*fl6)); + + if (t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS) + *dsfield = 0; + else + *dsfield = ip6_tclass(t->parms.flowinfo); + + if (t->parms.flags & IP6_TNL_F_USE_ORIG_FWMARK) + fl6->flowi6_mark = skb->mark; + else + fl6->flowi6_mark = t->parms.fwmark; + + fl6->flowi6_uid = sock_net_uid(dev_net(dev), NULL); + + return 0; +} + static struct ip_tunnel_info *skb_tunnel_info_txcheck(struct sk_buff *skb) { struct ip_tunnel_info *tun_info; @@ -868,20 +895,18 @@ static int ip6gre_xmit_other(struct sk_buff *skb, struct net_device *dev) struct ip6_tnl *t = netdev_priv(dev); int encap_limit = -1; struct flowi6 fl6; + __u8 dsfield = 0; __u32 mtu; int err; - if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) - encap_limit = t->parms.encap_limit; - - if (!t->parms.collect_md) - memcpy(&fl6, &t->fl.u.ip6, sizeof(fl6)); + if (!t->parms.collect_md && + prepare_ip6gre_xmit_other(skb, dev, &fl6, &dsfield, &encap_limit)) + return -1; err = gre_handle_offloads(skb, !!(t->parms.o_flags & TUNNEL_CSUM)); if (err) return err; - - err = __gre6_xmit(skb, dev, 0, &fl6, encap_limit, &mtu, skb->protocol); + err = __gre6_xmit(skb, dev, dsfield, &fl6, encap_limit, &mtu, skb->protocol); return err; } @@ -891,6 +916,7 @@ static netdev_tx_t ip6gre_tunnel_xmit(struct sk_buff *skb, { struct ip6_tnl *t = netdev_priv(dev); struct net_device_stats *stats = &t->dev->stats; + __be16 payload_protocol; int ret; if (!pskb_inet_may_pull(skb)) @@ -899,7 +925,8 @@ static netdev_tx_t ip6gre_tunnel_xmit(struct sk_buff *skb, if (!ip6_tnl_xmit_ctl(t, &t->parms.laddr, &t->parms.raddr)) goto tx_err; - switch (skb->protocol) { + payload_protocol = skb_protocol(skb, true); + switch (payload_protocol) { case htons(ETH_P_IP): ret = ip6gre_xmit_ipv4(skb, dev); break; @@ -1500,7 +1527,7 @@ static int ip6gre_tunnel_init_common(struct net_device *dev) } ip6gre_tnl_init_features(dev); - dev_hold_track(dev, &tunnel->dev_tracker, GFP_KERNEL); + netdev_hold(dev, &tunnel->dev_tracker, GFP_KERNEL); return 0; cleanup_dst_cache_init: @@ -1892,7 +1919,7 @@ static int ip6erspan_tap_init(struct net_device *dev) dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; ip6erspan_tnl_link_config(tunnel, 1); - dev_hold_track(dev, &tunnel->dev_tracker, GFP_KERNEL); + netdev_hold(dev, &tunnel->dev_tracker, GFP_KERNEL); return 0; cleanup_dst_cache_init: diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 19325b7600bb..3fda5634578c 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -381,7 +381,7 @@ ip6_tnl_dev_uninit(struct net_device *dev) else ip6_tnl_unlink(ip6n, t); dst_cache_reset(&t->dst_cache); - dev_put_track(dev, &t->dev_tracker); + netdev_put(dev, &t->dev_tracker); } /** @@ -796,7 +796,6 @@ static int __ip6_tnl_rcv(struct ip6_tnl *tunnel, struct sk_buff *skb, struct sk_buff *skb), bool log_ecn_err) { - struct pcpu_sw_netstats *tstats; const struct ipv6hdr *ipv6h = ipv6_hdr(skb); int err; @@ -856,11 +855,7 @@ static int __ip6_tnl_rcv(struct ip6_tnl *tunnel, struct sk_buff *skb, } } - tstats = this_cpu_ptr(tunnel->dev->tstats); - u64_stats_update_begin(&tstats->syncp); - tstats->rx_packets++; - tstats->rx_bytes += skb->len; - u64_stats_update_end(&tstats->syncp); + dev_sw_netstats_rx_add(tunnel->dev, skb->len); skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(tunnel->dev))); @@ -1085,10 +1080,13 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield, unsigned int eth_hlen = t->dev->type == ARPHRD_ETHER ? ETH_HLEN : 0; unsigned int psh_hlen = sizeof(struct ipv6hdr) + t->encap_hlen; unsigned int max_headroom = psh_hlen; + __be16 payload_protocol; bool use_cache = false; u8 hop_limit; int err = -1; + payload_protocol = skb_protocol(skb, true); + if (t->parms.collect_md) { hop_limit = skb_tunnel_info(skb)->key.ttl; goto route_lookup; @@ -1098,7 +1096,7 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield, /* NBMA tunnel */ if (ipv6_addr_any(&t->parms.raddr)) { - if (skb->protocol == htons(ETH_P_IPV6)) { + if (payload_protocol == htons(ETH_P_IPV6)) { struct in6_addr *addr6; struct neighbour *neigh; int addr_type; @@ -1119,7 +1117,7 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield, memcpy(&fl6->daddr, addr6, sizeof(fl6->daddr)); neigh_release(neigh); - } else if (skb->protocol == htons(ETH_P_IP)) { + } else if (payload_protocol == htons(ETH_P_IP)) { const struct rtable *rt = skb_rtable(skb); if (!rt) @@ -1230,9 +1228,9 @@ route_lookup: skb_dst_set(skb, dst); if (hop_limit == 0) { - if (skb->protocol == htons(ETH_P_IP)) + if (payload_protocol == htons(ETH_P_IP)) hop_limit = ip_hdr(skb)->ttl; - else if (skb->protocol == htons(ETH_P_IPV6)) + else if (payload_protocol == htons(ETH_P_IPV6)) hop_limit = ipv6_hdr(skb)->hop_limit; else hop_limit = ip6_dst_hoplimit(dst); @@ -1889,7 +1887,7 @@ ip6_tnl_dev_init_gen(struct net_device *dev) dev->min_mtu = ETH_MIN_MTU; dev->max_mtu = IP6_MAX_MTU - dev->hard_header_len; - dev_hold_track(dev, &t->dev_tracker, GFP_KERNEL); + netdev_hold(dev, &t->dev_tracker, GFP_KERNEL); return 0; destroy_dst: diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index 3a434d75925c..8fe59a79e800 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -293,7 +293,7 @@ static void vti6_dev_uninit(struct net_device *dev) RCU_INIT_POINTER(ip6n->tnls_wc[0], NULL); else vti6_tnl_unlink(ip6n, t); - dev_put_track(dev, &t->dev_tracker); + netdev_put(dev, &t->dev_tracker); } static int vti6_input_proto(struct sk_buff *skb, int nexthdr, __be32 spi, @@ -936,7 +936,7 @@ static inline int vti6_dev_init_gen(struct net_device *dev) dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); if (!dev->tstats) return -ENOMEM; - dev_hold_track(dev, &t->dev_tracker, GFP_KERNEL); + netdev_hold(dev, &t->dev_tracker, GFP_KERNEL); return 0; } diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 4e74bc61a3db..a9ba41648e36 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -62,7 +62,12 @@ struct ip6mr_result { Note that the changes are semaphored via rtnl_lock. */ -static DEFINE_RWLOCK(mrt_lock); +static DEFINE_SPINLOCK(mrt_lock); + +static struct net_device *vif_dev_read(const struct vif_device *vif) +{ + return rcu_dereference(vif->dev); +} /* Multicast router control variables */ @@ -85,11 +90,13 @@ static void ip6mr_free_table(struct mr_table *mrt); static void ip6_mr_forward(struct net *net, struct mr_table *mrt, struct net_device *dev, struct sk_buff *skb, struct mfc6_cache *cache); -static int ip6mr_cache_report(struct mr_table *mrt, struct sk_buff *pkt, +static int ip6mr_cache_report(const struct mr_table *mrt, struct sk_buff *pkt, mifi_t mifi, int assert); static void mr6_netlink_event(struct mr_table *mrt, struct mfc6_cache *mfc, int cmd); -static void mrt6msg_netlink_event(struct mr_table *mrt, struct sk_buff *pkt); +static void mrt6msg_netlink_event(const struct mr_table *mrt, struct sk_buff *pkt); +static int ip6mr_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, + struct netlink_ext_ack *extack); static int ip6mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb); static void mroute_clean_tables(struct mr_table *mrt, int flags); @@ -398,7 +405,7 @@ static void ip6mr_free_table(struct mr_table *mrt) */ static void *ip6mr_vif_seq_start(struct seq_file *seq, loff_t *pos) - __acquires(mrt_lock) + __acquires(RCU) { struct mr_vif_iter *iter = seq->private; struct net *net = seq_file_net(seq); @@ -410,14 +417,14 @@ static void *ip6mr_vif_seq_start(struct seq_file *seq, loff_t *pos) iter->mrt = mrt; - read_lock(&mrt_lock); + rcu_read_lock(); return mr_vif_seq_start(seq, pos); } static void ip6mr_vif_seq_stop(struct seq_file *seq, void *v) - __releases(mrt_lock) + __releases(RCU) { - read_unlock(&mrt_lock); + rcu_read_unlock(); } static int ip6mr_vif_seq_show(struct seq_file *seq, void *v) @@ -430,7 +437,11 @@ static int ip6mr_vif_seq_show(struct seq_file *seq, void *v) "Interface BytesIn PktsIn BytesOut PktsOut Flags\n"); } else { const struct vif_device *vif = v; - const char *name = vif->dev ? vif->dev->name : "none"; + const struct net_device *vif_dev; + const char *name; + + vif_dev = vif_dev_read(vif); + name = vif_dev ? vif_dev->name : "none"; seq_printf(seq, "%2td %-10s %8ld %7ld %8ld %7ld %05X\n", @@ -549,13 +560,11 @@ static int pim6_rcv(struct sk_buff *skb) if (ip6mr_fib_lookup(net, &fl6, &mrt) < 0) goto drop; - reg_vif_num = mrt->mroute_reg_vif_num; - read_lock(&mrt_lock); + /* Pairs with WRITE_ONCE() in mif6_add()/mif6_delete() */ + reg_vif_num = READ_ONCE(mrt->mroute_reg_vif_num); if (reg_vif_num >= 0) - reg_dev = mrt->vif_table[reg_vif_num].dev; - dev_hold(reg_dev); - read_unlock(&mrt_lock); + reg_dev = vif_dev_read(&mrt->vif_table[reg_vif_num]); if (!reg_dev) goto drop; @@ -570,7 +579,6 @@ static int pim6_rcv(struct sk_buff *skb) netif_rx(skb); - dev_put(reg_dev); return 0; drop: kfree_skb(skb); @@ -600,11 +608,12 @@ static netdev_tx_t reg_vif_xmit(struct sk_buff *skb, if (ip6mr_fib_lookup(net, &fl6, &mrt) < 0) goto tx_err; - read_lock(&mrt_lock); dev->stats.tx_bytes += skb->len; dev->stats.tx_packets++; - ip6mr_cache_report(mrt, skb, mrt->mroute_reg_vif_num, MRT6MSG_WHOLEPKT); - read_unlock(&mrt_lock); + rcu_read_lock(); + ip6mr_cache_report(mrt, skb, READ_ONCE(mrt->mroute_reg_vif_num), + MRT6MSG_WHOLEPKT); + rcu_read_unlock(); kfree_skb(skb); return NETDEV_TX_OK; @@ -670,10 +679,11 @@ failure: static int call_ip6mr_vif_entry_notifiers(struct net *net, enum fib_event_type event_type, struct vif_device *vif, + struct net_device *vif_dev, mifi_t vif_index, u32 tb_id) { return mr_call_vif_notifiers(net, RTNL_FAMILY_IP6MR, event_type, - vif, vif_index, tb_id, + vif, vif_dev, vif_index, tb_id, &net->ipv6.ipmr_seq); } @@ -698,23 +708,21 @@ static int mif6_delete(struct mr_table *mrt, int vifi, int notify, v = &mrt->vif_table[vifi]; - if (VIF_EXISTS(mrt, vifi)) - call_ip6mr_vif_entry_notifiers(read_pnet(&mrt->net), - FIB_EVENT_VIF_DEL, v, vifi, - mrt->id); - - write_lock_bh(&mrt_lock); - dev = v->dev; - v->dev = NULL; - - if (!dev) { - write_unlock_bh(&mrt_lock); + dev = rtnl_dereference(v->dev); + if (!dev) return -EADDRNOTAVAIL; - } + + call_ip6mr_vif_entry_notifiers(read_pnet(&mrt->net), + FIB_EVENT_VIF_DEL, v, dev, + vifi, mrt->id); + spin_lock(&mrt_lock); + RCU_INIT_POINTER(v->dev, NULL); #ifdef CONFIG_IPV6_PIMSM_V2 - if (vifi == mrt->mroute_reg_vif_num) - mrt->mroute_reg_vif_num = -1; + if (vifi == mrt->mroute_reg_vif_num) { + /* Pairs with READ_ONCE() in ip6mr_cache_report() and reg_vif_xmit() */ + WRITE_ONCE(mrt->mroute_reg_vif_num, -1); + } #endif if (vifi + 1 == mrt->maxvif) { @@ -723,10 +731,10 @@ static int mif6_delete(struct mr_table *mrt, int vifi, int notify, if (VIF_EXISTS(mrt, tmp)) break; } - mrt->maxvif = tmp + 1; + WRITE_ONCE(mrt->maxvif, tmp + 1); } - write_unlock_bh(&mrt_lock); + spin_unlock(&mrt_lock); dev_set_allmulti(dev, -1); @@ -741,7 +749,7 @@ static int mif6_delete(struct mr_table *mrt, int vifi, int notify, if ((v->flags & MIFF_REGISTER) && !notify) unregister_netdevice_queue(dev, head); - dev_put_track(dev, &v->dev_tracker); + netdev_put(dev, &v->dev_tracker); return 0; } @@ -826,7 +834,7 @@ static void ipmr_expire_process(struct timer_list *t) spin_unlock(&mfc_unres_lock); } -/* Fill oifs list. It is called under write locked mrt_lock. */ +/* Fill oifs list. It is called under locked mrt_lock. */ static void ip6mr_update_thresholds(struct mr_table *mrt, struct mr_mfc *cache, @@ -912,18 +920,18 @@ static int mif6_add(struct net *net, struct mr_table *mrt, MIFF_REGISTER); /* And finish update writing critical data */ - write_lock_bh(&mrt_lock); - v->dev = dev; + spin_lock(&mrt_lock); + rcu_assign_pointer(v->dev, dev); netdev_tracker_alloc(dev, &v->dev_tracker, GFP_ATOMIC); #ifdef CONFIG_IPV6_PIMSM_V2 if (v->flags & MIFF_REGISTER) - mrt->mroute_reg_vif_num = vifi; + WRITE_ONCE(mrt->mroute_reg_vif_num, vifi); #endif if (vifi + 1 > mrt->maxvif) - mrt->maxvif = vifi + 1; - write_unlock_bh(&mrt_lock); + WRITE_ONCE(mrt->maxvif, vifi + 1); + spin_unlock(&mrt_lock); call_ip6mr_vif_entry_notifiers(net, FIB_EVENT_VIF_ADD, - v, vifi, mrt->id); + v, dev, vifi, mrt->id); return 0; } @@ -1028,10 +1036,10 @@ static void ip6mr_cache_resolve(struct net *net, struct mr_table *mrt, /* * Bounce a cache query up to pim6sd and netlink. * - * Called under mrt_lock. + * Called under rcu_read_lock() */ -static int ip6mr_cache_report(struct mr_table *mrt, struct sk_buff *pkt, +static int ip6mr_cache_report(const struct mr_table *mrt, struct sk_buff *pkt, mifi_t mifi, int assert) { struct sock *mroute6_sk; @@ -1072,7 +1080,7 @@ static int ip6mr_cache_report(struct mr_table *mrt, struct sk_buff *pkt, if (assert == MRT6MSG_WRMIFWHOLE) msg->im6_mif = mifi; else - msg->im6_mif = mrt->mroute_reg_vif_num; + msg->im6_mif = READ_ONCE(mrt->mroute_reg_vif_num); msg->im6_pad = 0; msg->im6_src = ipv6_hdr(pkt)->saddr; msg->im6_dst = ipv6_hdr(pkt)->daddr; @@ -1107,10 +1115,8 @@ static int ip6mr_cache_report(struct mr_table *mrt, struct sk_buff *pkt, skb->ip_summed = CHECKSUM_UNNECESSARY; } - rcu_read_lock(); mroute6_sk = rcu_dereference(mrt->mroute_sk); if (!mroute6_sk) { - rcu_read_unlock(); kfree_skb(skb); return -EINVAL; } @@ -1119,7 +1125,7 @@ static int ip6mr_cache_report(struct mr_table *mrt, struct sk_buff *pkt, /* Deliver to user space multicast routing algorithms */ ret = sock_queue_rcv_skb(mroute6_sk, skb); - rcu_read_unlock(); + if (ret < 0) { net_warn_ratelimited("mroute6: pending queue full, dropping entries\n"); kfree_skb(skb); @@ -1243,7 +1249,7 @@ static int ip6mr_device_event(struct notifier_block *this, ip6mr_for_each_table(mrt, net) { v = &mrt->vif_table[0]; for (ct = 0; ct < mrt->maxvif; ct++, v++) { - if (v->dev == dev) + if (rcu_access_pointer(v->dev) == dev) mif6_delete(mrt, ct, 1, NULL); } } @@ -1262,7 +1268,7 @@ static int ip6mr_dump(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack) { return mr_dump(net, nb, RTNL_FAMILY_IP6MR, ip6mr_rules_dump, - ip6mr_mr_table_iter, &mrt_lock, extack); + ip6mr_mr_table_iter, extack); } static struct notifier_block ip6_mr_notifier = { @@ -1386,7 +1392,7 @@ int __init ip6_mr_init(void) } #endif err = rtnl_register_module(THIS_MODULE, RTNL_FAMILY_IP6MR, RTM_GETROUTE, - NULL, ip6mr_rtm_dumproute, 0); + ip6mr_rtm_getroute, ip6mr_rtm_dumproute, 0); if (err == 0) return 0; @@ -1437,12 +1443,12 @@ static int ip6mr_mfc_add(struct net *net, struct mr_table *mrt, &mfc->mf6cc_mcastgrp.sin6_addr, parent); rcu_read_unlock(); if (c) { - write_lock_bh(&mrt_lock); + spin_lock(&mrt_lock); c->_c.mfc_parent = mfc->mf6cc_parent; ip6mr_update_thresholds(mrt, &c->_c, ttls); if (!mrtsock) c->_c.mfc_flags |= MFC_STATIC; - write_unlock_bh(&mrt_lock); + spin_unlock(&mrt_lock); call_ip6mr_mfc_entry_notifiers(net, FIB_EVENT_ENTRY_REPLACE, c, mrt->id); mr6_netlink_event(mrt, c, RTM_NEWROUTE); @@ -1560,7 +1566,7 @@ static int ip6mr_sk_init(struct mr_table *mrt, struct sock *sk) struct net *net = sock_net(sk); rtnl_lock(); - write_lock_bh(&mrt_lock); + spin_lock(&mrt_lock); if (rtnl_dereference(mrt->mroute_sk)) { err = -EADDRINUSE; } else { @@ -1568,7 +1574,7 @@ static int ip6mr_sk_init(struct mr_table *mrt, struct sock *sk) sock_set_flag(sk, SOCK_RCU_FREE); atomic_inc(&net->ipv6.devconf_all->mc_forwarding); } - write_unlock_bh(&mrt_lock); + spin_unlock(&mrt_lock); if (!err) inet6_netconf_notify_devconf(net, RTM_NEWNETCONF, @@ -1598,14 +1604,14 @@ int ip6mr_sk_done(struct sock *sk) rtnl_lock(); ip6mr_for_each_table(mrt, net) { if (sk == rtnl_dereference(mrt->mroute_sk)) { - write_lock_bh(&mrt_lock); + spin_lock(&mrt_lock); RCU_INIT_POINTER(mrt->mroute_sk, NULL); /* Note that mroute_sk had SOCK_RCU_FREE set, * so the RCU grace period before sk freeing * is guaranteed by sk_destruct() */ atomic_dec(&devconf->mc_forwarding); - write_unlock_bh(&mrt_lock); + spin_unlock(&mrt_lock); inet6_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_MC_FORWARDING, NETCONFA_IFINDEX_ALL, @@ -1891,20 +1897,20 @@ int ip6mr_ioctl(struct sock *sk, int cmd, void __user *arg) if (vr.mifi >= mrt->maxvif) return -EINVAL; vr.mifi = array_index_nospec(vr.mifi, mrt->maxvif); - read_lock(&mrt_lock); + rcu_read_lock(); vif = &mrt->vif_table[vr.mifi]; if (VIF_EXISTS(mrt, vr.mifi)) { - vr.icount = vif->pkt_in; - vr.ocount = vif->pkt_out; - vr.ibytes = vif->bytes_in; - vr.obytes = vif->bytes_out; - read_unlock(&mrt_lock); + vr.icount = READ_ONCE(vif->pkt_in); + vr.ocount = READ_ONCE(vif->pkt_out); + vr.ibytes = READ_ONCE(vif->bytes_in); + vr.obytes = READ_ONCE(vif->bytes_out); + rcu_read_unlock(); if (copy_to_user(arg, &vr, sizeof(vr))) return -EFAULT; return 0; } - read_unlock(&mrt_lock); + rcu_read_unlock(); return -EADDRNOTAVAIL; case SIOCGETSGCNT_IN6: if (copy_from_user(&sr, arg, sizeof(sr))) @@ -1966,20 +1972,20 @@ int ip6mr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg) if (vr.mifi >= mrt->maxvif) return -EINVAL; vr.mifi = array_index_nospec(vr.mifi, mrt->maxvif); - read_lock(&mrt_lock); + rcu_read_lock(); vif = &mrt->vif_table[vr.mifi]; if (VIF_EXISTS(mrt, vr.mifi)) { - vr.icount = vif->pkt_in; - vr.ocount = vif->pkt_out; - vr.ibytes = vif->bytes_in; - vr.obytes = vif->bytes_out; - read_unlock(&mrt_lock); + vr.icount = READ_ONCE(vif->pkt_in); + vr.ocount = READ_ONCE(vif->pkt_out); + vr.ibytes = READ_ONCE(vif->bytes_in); + vr.obytes = READ_ONCE(vif->bytes_out); + rcu_read_unlock(); if (copy_to_user(arg, &vr, sizeof(vr))) return -EFAULT; return 0; } - read_unlock(&mrt_lock); + rcu_read_unlock(); return -EADDRNOTAVAIL; case SIOCGETSGCNT_IN6: if (copy_from_user(&sr, arg, sizeof(sr))) @@ -2021,21 +2027,22 @@ static inline int ip6mr_forward2_finish(struct net *net, struct sock *sk, struct static int ip6mr_forward2(struct net *net, struct mr_table *mrt, struct sk_buff *skb, int vifi) { - struct ipv6hdr *ipv6h; struct vif_device *vif = &mrt->vif_table[vifi]; - struct net_device *dev; + struct net_device *vif_dev; + struct ipv6hdr *ipv6h; struct dst_entry *dst; struct flowi6 fl6; - if (!vif->dev) + vif_dev = vif_dev_read(vif); + if (!vif_dev) goto out_free; #ifdef CONFIG_IPV6_PIMSM_V2 if (vif->flags & MIFF_REGISTER) { - vif->pkt_out++; - vif->bytes_out += skb->len; - vif->dev->stats.tx_bytes += skb->len; - vif->dev->stats.tx_packets++; + WRITE_ONCE(vif->pkt_out, vif->pkt_out + 1); + WRITE_ONCE(vif->bytes_out, vif->bytes_out + skb->len); + vif_dev->stats.tx_bytes += skb->len; + vif_dev->stats.tx_packets++; ip6mr_cache_report(mrt, skb, vifi, MRT6MSG_WHOLEPKT); goto out_free; } @@ -2068,14 +2075,13 @@ static int ip6mr_forward2(struct net *net, struct mr_table *mrt, * not mrouter) cannot join to more than one interface - it will * result in receiving multiple packets. */ - dev = vif->dev; - skb->dev = dev; - vif->pkt_out++; - vif->bytes_out += skb->len; + skb->dev = vif_dev; + WRITE_ONCE(vif->pkt_out, vif->pkt_out + 1); + WRITE_ONCE(vif->bytes_out, vif->bytes_out + skb->len); /* We are about to write */ /* XXX: extension headers? */ - if (skb_cow(skb, sizeof(*ipv6h) + LL_RESERVED_SPACE(dev))) + if (skb_cow(skb, sizeof(*ipv6h) + LL_RESERVED_SPACE(vif_dev))) goto out_free; ipv6h = ipv6_hdr(skb); @@ -2084,7 +2090,7 @@ static int ip6mr_forward2(struct net *net, struct mr_table *mrt, IP6CB(skb)->flags |= IP6SKB_FORWARDED; return NF_HOOK(NFPROTO_IPV6, NF_INET_FORWARD, - net, NULL, skb, skb->dev, dev, + net, NULL, skb, skb->dev, vif_dev, ip6mr_forward2_finish); out_free: @@ -2092,17 +2098,20 @@ out_free: return 0; } +/* Called with rcu_read_lock() */ static int ip6mr_find_vif(struct mr_table *mrt, struct net_device *dev) { int ct; - for (ct = mrt->maxvif - 1; ct >= 0; ct--) { - if (mrt->vif_table[ct].dev == dev) + /* Pairs with WRITE_ONCE() in mif6_delete()/mif6_add() */ + for (ct = READ_ONCE(mrt->maxvif) - 1; ct >= 0; ct--) { + if (rcu_access_pointer(mrt->vif_table[ct].dev) == dev) break; } return ct; } +/* Called under rcu_read_lock() */ static void ip6_mr_forward(struct net *net, struct mr_table *mrt, struct net_device *dev, struct sk_buff *skb, struct mfc6_cache *c) @@ -2122,20 +2131,16 @@ static void ip6_mr_forward(struct net *net, struct mr_table *mrt, /* For an (*,G) entry, we only check that the incoming * interface is part of the static tree. */ - rcu_read_lock(); cache_proxy = mr_mfc_find_any_parent(mrt, vif); if (cache_proxy && - cache_proxy->_c.mfc_un.res.ttls[true_vifi] < 255) { - rcu_read_unlock(); + cache_proxy->_c.mfc_un.res.ttls[true_vifi] < 255) goto forward; - } - rcu_read_unlock(); } /* * Wrong interface: drop packet and (maybe) send PIM assert. */ - if (mrt->vif_table[vif].dev != dev) { + if (rcu_access_pointer(mrt->vif_table[vif].dev) != dev) { c->_c.mfc_un.res.wrong_if++; if (true_vifi >= 0 && mrt->mroute_do_assert && @@ -2159,8 +2164,10 @@ static void ip6_mr_forward(struct net *net, struct mr_table *mrt, } forward: - mrt->vif_table[vif].pkt_in++; - mrt->vif_table[vif].bytes_in += skb->len; + WRITE_ONCE(mrt->vif_table[vif].pkt_in, + mrt->vif_table[vif].pkt_in + 1); + WRITE_ONCE(mrt->vif_table[vif].bytes_in, + mrt->vif_table[vif].bytes_in + skb->len); /* * Forward the frame @@ -2238,7 +2245,6 @@ int ip6_mr_input(struct sk_buff *skb) return err; } - read_lock(&mrt_lock); cache = ip6mr_cache_find(mrt, &ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr); if (!cache) { @@ -2259,19 +2265,15 @@ int ip6_mr_input(struct sk_buff *skb) vif = ip6mr_find_vif(mrt, dev); if (vif >= 0) { int err = ip6mr_cache_unresolved(mrt, vif, skb, dev); - read_unlock(&mrt_lock); return err; } - read_unlock(&mrt_lock); kfree_skb(skb); return -ENODEV; } ip6_mr_forward(net, mrt, dev, skb, cache); - read_unlock(&mrt_lock); - return 0; } @@ -2287,7 +2289,7 @@ int ip6mr_get_route(struct net *net, struct sk_buff *skb, struct rtmsg *rtm, if (!mrt) return -ENOENT; - read_lock(&mrt_lock); + rcu_read_lock(); cache = ip6mr_cache_find(mrt, &rt->rt6i_src.addr, &rt->rt6i_dst.addr); if (!cache && skb->dev) { int vif = ip6mr_find_vif(mrt, skb->dev); @@ -2305,14 +2307,14 @@ int ip6mr_get_route(struct net *net, struct sk_buff *skb, struct rtmsg *rtm, dev = skb->dev; if (!dev || (vif = ip6mr_find_vif(mrt, dev)) < 0) { - read_unlock(&mrt_lock); + rcu_read_unlock(); return -ENODEV; } /* really correct? */ skb2 = alloc_skb(sizeof(struct ipv6hdr), GFP_ATOMIC); if (!skb2) { - read_unlock(&mrt_lock); + rcu_read_unlock(); return -ENOMEM; } @@ -2335,13 +2337,13 @@ int ip6mr_get_route(struct net *net, struct sk_buff *skb, struct rtmsg *rtm, iph->daddr = rt->rt6i_dst.addr; err = ip6mr_cache_unresolved(mrt, vif, skb2, dev); - read_unlock(&mrt_lock); + rcu_read_unlock(); return err; } err = mr_fill_mroute(mrt, skb, &cache->_c, rtm); - read_unlock(&mrt_lock); + rcu_read_unlock(); return err; } @@ -2460,7 +2462,7 @@ static size_t mrt6msg_netlink_msgsize(size_t payloadlen) return len; } -static void mrt6msg_netlink_event(struct mr_table *mrt, struct sk_buff *pkt) +static void mrt6msg_netlink_event(const struct mr_table *mrt, struct sk_buff *pkt) { struct net *net = read_pnet(&mrt->net); struct nlmsghdr *nlh; @@ -2508,6 +2510,95 @@ errout: rtnl_set_sk_err(net, RTNLGRP_IPV6_MROUTE_R, -ENOBUFS); } +static const struct nla_policy ip6mr_getroute_policy[RTA_MAX + 1] = { + [RTA_SRC] = NLA_POLICY_EXACT_LEN(sizeof(struct in6_addr)), + [RTA_DST] = NLA_POLICY_EXACT_LEN(sizeof(struct in6_addr)), + [RTA_TABLE] = { .type = NLA_U32 }, +}; + +static int ip6mr_rtm_valid_getroute_req(struct sk_buff *skb, + const struct nlmsghdr *nlh, + struct nlattr **tb, + struct netlink_ext_ack *extack) +{ + struct rtmsg *rtm; + int err; + + err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, ip6mr_getroute_policy, + extack); + if (err) + return err; + + rtm = nlmsg_data(nlh); + if ((rtm->rtm_src_len && rtm->rtm_src_len != 128) || + (rtm->rtm_dst_len && rtm->rtm_dst_len != 128) || + rtm->rtm_tos || rtm->rtm_table || rtm->rtm_protocol || + rtm->rtm_scope || rtm->rtm_type || rtm->rtm_flags) { + NL_SET_ERR_MSG_MOD(extack, + "Invalid values in header for multicast route get request"); + return -EINVAL; + } + + if ((tb[RTA_SRC] && !rtm->rtm_src_len) || + (tb[RTA_DST] && !rtm->rtm_dst_len)) { + NL_SET_ERR_MSG_MOD(extack, "rtm_src_len and rtm_dst_len must be 128 for IPv6"); + return -EINVAL; + } + + return 0; +} + +static int ip6mr_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, + struct netlink_ext_ack *extack) +{ + struct net *net = sock_net(in_skb->sk); + struct in6_addr src = {}, grp = {}; + struct nlattr *tb[RTA_MAX + 1]; + struct mfc6_cache *cache; + struct mr_table *mrt; + struct sk_buff *skb; + u32 tableid; + int err; + + err = ip6mr_rtm_valid_getroute_req(in_skb, nlh, tb, extack); + if (err < 0) + return err; + + if (tb[RTA_SRC]) + src = nla_get_in6_addr(tb[RTA_SRC]); + if (tb[RTA_DST]) + grp = nla_get_in6_addr(tb[RTA_DST]); + tableid = tb[RTA_TABLE] ? nla_get_u32(tb[RTA_TABLE]) : 0; + + mrt = ip6mr_get_table(net, tableid ?: RT_TABLE_DEFAULT); + if (!mrt) { + NL_SET_ERR_MSG_MOD(extack, "MR table does not exist"); + return -ENOENT; + } + + /* entries are added/deleted only under RTNL */ + rcu_read_lock(); + cache = ip6mr_cache_find(mrt, &src, &grp); + rcu_read_unlock(); + if (!cache) { + NL_SET_ERR_MSG_MOD(extack, "MR cache entry not found"); + return -ENOENT; + } + + skb = nlmsg_new(mr6_msgsize(false, mrt->maxvif), GFP_KERNEL); + if (!skb) + return -ENOBUFS; + + err = ip6mr_fill_mroute(mrt, skb, NETLINK_CB(in_skb).portid, + nlh->nlmsg_seq, cache, RTM_NEWROUTE, 0); + if (err < 0) { + kfree_skb(skb); + return err; + } + + return rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid); +} + static int ip6mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb) { const struct nlmsghdr *nlh = cb->nlh; diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index b0dfe97ea4ee..98453693e400 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -128,6 +128,7 @@ struct neigh_table nd_tbl = { [NEIGH_VAR_RETRANS_TIME] = ND_RETRANS_TIMER, [NEIGH_VAR_BASE_REACHABLE_TIME] = ND_REACHABLE_TIME, [NEIGH_VAR_DELAY_PROBE_TIME] = 5 * HZ, + [NEIGH_VAR_INTERVAL_PROBE_TIME_MS] = 5 * HZ, [NEIGH_VAR_GC_STALETIME] = 60 * HZ, [NEIGH_VAR_QUEUE_LEN_BYTES] = SK_WMEM_MAX, [NEIGH_VAR_PROXY_QLEN] = 64, @@ -966,6 +967,25 @@ out: in6_dev_put(idev); } +static int accept_untracked_na(struct net_device *dev, struct in6_addr *saddr) +{ + struct inet6_dev *idev = __in6_dev_get(dev); + + switch (idev->cnf.accept_untracked_na) { + case 0: /* Don't accept untracked na (absent in neighbor cache) */ + return 0; + case 1: /* Create new entries from na if currently untracked */ + return 1; + case 2: /* Create new entries from untracked na only if saddr is in the + * same subnet as an address configured on the interface that + * received the na + */ + return !!ipv6_chk_prefix(saddr, dev); + default: + return 0; + } +} + static void ndisc_recv_na(struct sk_buff *skb) { struct nd_msg *msg = (struct nd_msg *)skb_transport_header(skb); @@ -1060,11 +1080,11 @@ static void ndisc_recv_na(struct sk_buff *skb) * Note that we don't do a (daddr == all-routers-mcast) check. */ new_state = msg->icmph.icmp6_solicited ? NUD_REACHABLE : NUD_STALE; - if (!neigh && lladdr && - idev && idev->cnf.forwarding && - idev->cnf.accept_untracked_na) { - neigh = neigh_create(&nd_tbl, &msg->target, dev); - new_state = NUD_STALE; + if (!neigh && lladdr && idev && idev->cnf.forwarding) { + if (accept_untracked_na(dev, saddr)) { + neigh = neigh_create(&nd_tbl, &msg->target, dev); + new_state = NUD_STALE; + } } if (neigh && !IS_ERR(neigh)) { diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c index 8c6c2d82c1cd..91b840514656 100644 --- a/net/ipv6/ping.c +++ b/net/ipv6/ping.c @@ -69,6 +69,8 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (err) return err; + memset(&fl6, 0, sizeof(fl6)); + if (msg->msg_name) { DECLARE_SOCKADDR(struct sockaddr_in6 *, u, msg->msg_name); if (msg->msg_namelen < sizeof(*u)) @@ -77,12 +79,15 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) return -EAFNOSUPPORT; } daddr = &(u->sin6_addr); + if (np->sndflow) + fl6.flowlabel = u->sin6_flowinfo & IPV6_FLOWINFO_MASK; if (__ipv6_addr_needs_scope_id(ipv6_addr_type(daddr))) oif = u->sin6_scope_id; } else { if (sk->sk_state != TCP_ESTABLISHED) return -EDESTADDRREQ; daddr = &sk->sk_v6_daddr; + fl6.flowlabel = np->flow_label; } if (!oif) @@ -106,7 +111,6 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) ipc6.sockc.tsflags = sk->sk_tsflags; ipc6.sockc.mark = sk->sk_mark; - memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_oif = oif; if (msg->msg_controllen) { diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 3b7cbd522b54..722de9dd0ff7 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -61,46 +61,30 @@ #define ICMPV6_HDRLEN 4 /* ICMPv6 header, RFC 4443 Section 2.1 */ -struct raw_hashinfo raw_v6_hashinfo = { - .lock = __RW_LOCK_UNLOCKED(raw_v6_hashinfo.lock), -}; +struct raw_hashinfo raw_v6_hashinfo; EXPORT_SYMBOL_GPL(raw_v6_hashinfo); -struct sock *__raw_v6_lookup(struct net *net, struct sock *sk, - unsigned short num, const struct in6_addr *loc_addr, - const struct in6_addr *rmt_addr, int dif, int sdif) +bool raw_v6_match(struct net *net, struct sock *sk, unsigned short num, + const struct in6_addr *loc_addr, + const struct in6_addr *rmt_addr, int dif, int sdif) { - bool is_multicast = ipv6_addr_is_multicast(loc_addr); - - sk_for_each_from(sk) - if (inet_sk(sk)->inet_num == num) { - - if (!net_eq(sock_net(sk), net)) - continue; - - if (!ipv6_addr_any(&sk->sk_v6_daddr) && - !ipv6_addr_equal(&sk->sk_v6_daddr, rmt_addr)) - continue; - - if (!raw_sk_bound_dev_eq(net, sk->sk_bound_dev_if, - dif, sdif)) - continue; - - if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr)) { - if (ipv6_addr_equal(&sk->sk_v6_rcv_saddr, loc_addr)) - goto found; - if (is_multicast && - inet6_mc_check(sk, loc_addr, rmt_addr)) - goto found; - continue; - } - goto found; - } - sk = NULL; -found: - return sk; + if (inet_sk(sk)->inet_num != num || + !net_eq(sock_net(sk), net) || + (!ipv6_addr_any(&sk->sk_v6_daddr) && + !ipv6_addr_equal(&sk->sk_v6_daddr, rmt_addr)) || + !raw_sk_bound_dev_eq(net, sk->sk_bound_dev_if, + dif, sdif)) + return false; + + if (ipv6_addr_any(&sk->sk_v6_rcv_saddr) || + ipv6_addr_equal(&sk->sk_v6_rcv_saddr, loc_addr) || + (ipv6_addr_is_multicast(loc_addr) && + inet6_mc_check(sk, loc_addr, rmt_addr))) + return true; + + return false; } -EXPORT_SYMBOL_GPL(__raw_v6_lookup); +EXPORT_SYMBOL_GPL(raw_v6_match); /* * 0 - deliver @@ -156,31 +140,27 @@ EXPORT_SYMBOL(rawv6_mh_filter_unregister); */ static bool ipv6_raw_deliver(struct sk_buff *skb, int nexthdr) { + struct net *net = dev_net(skb->dev); + struct hlist_nulls_head *hlist; + struct hlist_nulls_node *hnode; const struct in6_addr *saddr; const struct in6_addr *daddr; struct sock *sk; bool delivered = false; __u8 hash; - struct net *net; saddr = &ipv6_hdr(skb)->saddr; daddr = saddr + 1; hash = nexthdr & (RAW_HTABLE_SIZE - 1); - - read_lock(&raw_v6_hashinfo.lock); - sk = sk_head(&raw_v6_hashinfo.ht[hash]); - - if (!sk) - goto out; - - net = dev_net(skb->dev); - sk = __raw_v6_lookup(net, sk, nexthdr, daddr, saddr, - inet6_iif(skb), inet6_sdif(skb)); - - while (sk) { + hlist = &raw_v6_hashinfo.ht[hash]; + rcu_read_lock(); + sk_nulls_for_each(sk, hnode, hlist) { int filtered; + if (!raw_v6_match(net, sk, nexthdr, daddr, saddr, + inet6_iif(skb), inet6_sdif(skb))) + continue; delivered = true; switch (nexthdr) { case IPPROTO_ICMPV6: @@ -219,23 +199,14 @@ static bool ipv6_raw_deliver(struct sk_buff *skb, int nexthdr) rawv6_rcv(sk, clone); } } - sk = __raw_v6_lookup(net, sk_next(sk), nexthdr, daddr, saddr, - inet6_iif(skb), inet6_sdif(skb)); } -out: - read_unlock(&raw_v6_hashinfo.lock); + rcu_read_unlock(); return delivered; } bool raw6_local_deliver(struct sk_buff *skb, int nexthdr) { - struct sock *raw_sk; - - raw_sk = sk_head(&raw_v6_hashinfo.ht[nexthdr & (RAW_HTABLE_SIZE - 1)]); - if (raw_sk && !ipv6_raw_deliver(skb, nexthdr)) - raw_sk = NULL; - - return raw_sk != NULL; + return ipv6_raw_deliver(skb, nexthdr); } /* This cleans up af_inet6 a bit. -DaveM */ @@ -361,30 +332,25 @@ static void rawv6_err(struct sock *sk, struct sk_buff *skb, void raw6_icmp_error(struct sk_buff *skb, int nexthdr, u8 type, u8 code, int inner_offset, __be32 info) { + struct net *net = dev_net(skb->dev); + struct hlist_nulls_head *hlist; + struct hlist_nulls_node *hnode; struct sock *sk; int hash; - const struct in6_addr *saddr, *daddr; - struct net *net; hash = nexthdr & (RAW_HTABLE_SIZE - 1); - - read_lock(&raw_v6_hashinfo.lock); - sk = sk_head(&raw_v6_hashinfo.ht[hash]); - if (sk) { + hlist = &raw_v6_hashinfo.ht[hash]; + rcu_read_lock(); + sk_nulls_for_each(sk, hnode, hlist) { /* Note: ipv6_hdr(skb) != skb->data */ const struct ipv6hdr *ip6h = (const struct ipv6hdr *)skb->data; - saddr = &ip6h->saddr; - daddr = &ip6h->daddr; - net = dev_net(skb->dev); - - while ((sk = __raw_v6_lookup(net, sk, nexthdr, saddr, daddr, - inet6_iif(skb), inet6_iif(skb)))) { - rawv6_err(sk, skb, NULL, type, code, - inner_offset, info); - sk = sk_next(sk); - } + + if (!raw_v6_match(net, sk, nexthdr, &ip6h->saddr, &ip6h->daddr, + inet6_iif(skb), inet6_iif(skb))) + continue; + rawv6_err(sk, skb, NULL, type, code, inner_offset, info); } - read_unlock(&raw_v6_hashinfo.lock); + rcu_read_unlock(); } static inline int rawv6_rcv_skb(struct sock *sk, struct sk_buff *skb) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 916417944ec8..69252eb462b2 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -182,9 +182,9 @@ static void rt6_uncached_list_flush_dev(struct net_device *dev) if (rt_dev == dev) { rt->dst.dev = blackhole_netdev; - dev_replace_track(rt_dev, blackhole_netdev, - &rt->dst.dev_tracker, - GFP_ATOMIC); + netdev_ref_replace(rt_dev, blackhole_netdev, + &rt->dst.dev_tracker, + GFP_ATOMIC); handled = true; } if (handled) @@ -607,7 +607,7 @@ static void rt6_probe_deferred(struct work_struct *w) addrconf_addr_solict_mult(&work->target, &mcaddr); ndisc_send_ns(work->dev, &work->target, &mcaddr, NULL, 0); - dev_put_track(work->dev, &work->dev_tracker); + netdev_put(work->dev, &work->dev_tracker); kfree(work); } @@ -661,7 +661,7 @@ static void rt6_probe(struct fib6_nh *fib6_nh) } else { INIT_WORK(&work->work, rt6_probe_deferred); work->target = *nh_gw; - dev_hold_track(dev, &work->dev_tracker, GFP_ATOMIC); + netdev_hold(dev, &work->dev_tracker, GFP_ATOMIC); work->dev = dev; schedule_work(&work->work); } @@ -5941,7 +5941,7 @@ int rt6_dump_route(struct fib6_info *rt, void *p_arg, unsigned int skip) rcu_read_unlock(); if (err) - return count += w.count; + return count + w.count; } return -1; diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c index e756ba705fd9..34db881204d2 100644 --- a/net/ipv6/seg6_iptunnel.c +++ b/net/ipv6/seg6_iptunnel.c @@ -36,9 +36,11 @@ static size_t seg6_lwt_headroom(struct seg6_iptunnel_encap *tuninfo) case SEG6_IPTUN_MODE_INLINE: break; case SEG6_IPTUN_MODE_ENCAP: + case SEG6_IPTUN_MODE_ENCAP_RED: head = sizeof(struct ipv6hdr); break; case SEG6_IPTUN_MODE_L2ENCAP: + case SEG6_IPTUN_MODE_L2ENCAP_RED: return 0; } @@ -197,6 +199,124 @@ int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto) } EXPORT_SYMBOL_GPL(seg6_do_srh_encap); +/* encapsulate an IPv6 packet within an outer IPv6 header with reduced SRH */ +static int seg6_do_srh_encap_red(struct sk_buff *skb, + struct ipv6_sr_hdr *osrh, int proto) +{ + __u8 first_seg = osrh->first_segment; + struct dst_entry *dst = skb_dst(skb); + struct net *net = dev_net(dst->dev); + struct ipv6hdr *hdr, *inner_hdr; + int hdrlen = ipv6_optlen(osrh); + int red_tlv_offset, tlv_offset; + struct ipv6_sr_hdr *isrh; + bool skip_srh = false; + __be32 flowlabel; + int tot_len, err; + int red_hdrlen; + int tlvs_len; + + if (first_seg > 0) { + red_hdrlen = hdrlen - sizeof(struct in6_addr); + } else { + /* NOTE: if tag/flags and/or other TLVs are introduced in the + * seg6_iptunnel infrastructure, they should be considered when + * deciding to skip the SRH. + */ + skip_srh = !sr_has_hmac(osrh); + + red_hdrlen = skip_srh ? 0 : hdrlen; + } + + tot_len = red_hdrlen + sizeof(struct ipv6hdr); + + err = skb_cow_head(skb, tot_len + skb->mac_len); + if (unlikely(err)) + return err; + + inner_hdr = ipv6_hdr(skb); + flowlabel = seg6_make_flowlabel(net, skb, inner_hdr); + + skb_push(skb, tot_len); + skb_reset_network_header(skb); + skb_mac_header_rebuild(skb); + hdr = ipv6_hdr(skb); + + /* based on seg6_do_srh_encap() */ + if (skb->protocol == htons(ETH_P_IPV6)) { + ip6_flow_hdr(hdr, ip6_tclass(ip6_flowinfo(inner_hdr)), + flowlabel); + hdr->hop_limit = inner_hdr->hop_limit; + } else { + ip6_flow_hdr(hdr, 0, flowlabel); + hdr->hop_limit = ip6_dst_hoplimit(skb_dst(skb)); + + memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); + IP6CB(skb)->iif = skb->skb_iif; + } + + /* no matter if we have to skip the SRH or not, the first segment + * always comes in the pushed IPv6 header. + */ + hdr->daddr = osrh->segments[first_seg]; + + if (skip_srh) { + hdr->nexthdr = proto; + + set_tun_src(net, dst->dev, &hdr->daddr, &hdr->saddr); + goto out; + } + + /* we cannot skip the SRH, slow path */ + + hdr->nexthdr = NEXTHDR_ROUTING; + isrh = (void *)hdr + sizeof(struct ipv6hdr); + + if (unlikely(!first_seg)) { + /* this is a very rare case; we have only one SID but + * we cannot skip the SRH since we are carrying some + * other info. + */ + memcpy(isrh, osrh, hdrlen); + goto srcaddr; + } + + tlv_offset = sizeof(*osrh) + (first_seg + 1) * sizeof(struct in6_addr); + red_tlv_offset = tlv_offset - sizeof(struct in6_addr); + + memcpy(isrh, osrh, red_tlv_offset); + + tlvs_len = hdrlen - tlv_offset; + if (unlikely(tlvs_len > 0)) { + const void *s = (const void *)osrh + tlv_offset; + void *d = (void *)isrh + red_tlv_offset; + + memcpy(d, s, tlvs_len); + } + + --isrh->first_segment; + isrh->hdrlen -= 2; + +srcaddr: + isrh->nexthdr = proto; + set_tun_src(net, dst->dev, &hdr->daddr, &hdr->saddr); + +#ifdef CONFIG_IPV6_SEG6_HMAC + if (unlikely(!skip_srh && sr_has_hmac(isrh))) { + err = seg6_push_hmac(net, &hdr->saddr, isrh); + if (unlikely(err)) + return err; + } +#endif + +out: + hdr->payload_len = htons(skb->len - sizeof(struct ipv6hdr)); + + skb_postpush_rcsum(skb, hdr, tot_len); + + return 0; +} + /* insert an SRH within an IPv6 packet, just after the IPv6 header */ int seg6_do_srh_inline(struct sk_buff *skb, struct ipv6_sr_hdr *osrh) { @@ -269,6 +389,7 @@ static int seg6_do_srh(struct sk_buff *skb) return err; break; case SEG6_IPTUN_MODE_ENCAP: + case SEG6_IPTUN_MODE_ENCAP_RED: err = iptunnel_handle_offloads(skb, SKB_GSO_IPXIP6); if (err) return err; @@ -280,7 +401,11 @@ static int seg6_do_srh(struct sk_buff *skb) else return -EINVAL; - err = seg6_do_srh_encap(skb, tinfo->srh, proto); + if (tinfo->mode == SEG6_IPTUN_MODE_ENCAP) + err = seg6_do_srh_encap(skb, tinfo->srh, proto); + else + err = seg6_do_srh_encap_red(skb, tinfo->srh, proto); + if (err) return err; @@ -289,6 +414,7 @@ static int seg6_do_srh(struct sk_buff *skb) skb->protocol = htons(ETH_P_IPV6); break; case SEG6_IPTUN_MODE_L2ENCAP: + case SEG6_IPTUN_MODE_L2ENCAP_RED: if (!skb_mac_header_was_set(skb)) return -EINVAL; @@ -298,7 +424,13 @@ static int seg6_do_srh(struct sk_buff *skb) skb_mac_header_rebuild(skb); skb_push(skb, skb->mac_len); - err = seg6_do_srh_encap(skb, tinfo->srh, IPPROTO_ETHERNET); + if (tinfo->mode == SEG6_IPTUN_MODE_L2ENCAP) + err = seg6_do_srh_encap(skb, tinfo->srh, + IPPROTO_ETHERNET); + else + err = seg6_do_srh_encap_red(skb, tinfo->srh, + IPPROTO_ETHERNET); + if (err) return err; @@ -517,6 +649,10 @@ static int seg6_build_state(struct net *net, struct nlattr *nla, break; case SEG6_IPTUN_MODE_L2ENCAP: break; + case SEG6_IPTUN_MODE_ENCAP_RED: + break; + case SEG6_IPTUN_MODE_L2ENCAP_RED: + break; default: return -EINVAL; } diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 6bcd5e419a08..6b73b7a5f175 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -519,7 +519,7 @@ static void ipip6_tunnel_uninit(struct net_device *dev) ipip6_tunnel_del_prl(tunnel, NULL); } dst_cache_reset(&tunnel->dst_cache); - dev_put_track(dev, &tunnel->dev_tracker); + netdev_put(dev, &tunnel->dev_tracker); } static int ipip6_err(struct sk_buff *skb, u32 info) @@ -684,8 +684,6 @@ static int ipip6_rcv(struct sk_buff *skb) tunnel = ipip6_tunnel_lookup(dev_net(skb->dev), skb->dev, iph->saddr, iph->daddr, sifindex); if (tunnel) { - struct pcpu_sw_netstats *tstats; - if (tunnel->parms.iph.protocol != IPPROTO_IPV6 && tunnel->parms.iph.protocol != 0) goto out; @@ -722,11 +720,7 @@ static int ipip6_rcv(struct sk_buff *skb) } } - tstats = this_cpu_ptr(tunnel->dev->tstats); - u64_stats_update_begin(&tstats->syncp); - tstats->rx_packets++; - tstats->rx_bytes += skb->len; - u64_stats_update_end(&tstats->syncp); + dev_sw_netstats_rx_add(tunnel->dev, skb->len); netif_rx(skb); @@ -1461,7 +1455,7 @@ static int ipip6_tunnel_init(struct net_device *dev) dev->tstats = NULL; return err; } - dev_hold_track(dev, &tunnel->dev_tracker, GFP_KERNEL); + netdev_hold(dev, &tunnel->dev_tracker, GFP_KERNEL); return 0; } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index be09941fe6d9..e54eee80ce5f 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -952,7 +952,10 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32 * Underlying function will use this to retrieve the network * namespace */ - dst = ip6_dst_lookup_flow(sock_net(ctl_sk), ctl_sk, &fl6, NULL); + if (sk && sk->sk_state != TCP_TIME_WAIT) + dst = ip6_dst_lookup_flow(net, sk, &fl6, NULL); /*sk's xfrm_policy can be referred*/ + else + dst = ip6_dst_lookup_flow(net, ctl_sk, &fl6, NULL); if (!IS_ERR(dst)) { skb_dst_set(buff, dst); ip6_xmit(ctl_sk, buff, &fl6, fl6.flowi6_mark, NULL, @@ -2159,7 +2162,10 @@ struct proto tcpv6_prot = { .leave_memory_pressure = tcp_leave_memory_pressure, .stream_memory_free = tcp_stream_memory_free, .sockets_allocated = &tcp_sockets_allocated, + .memory_allocated = &tcp_memory_allocated, + .per_cpu_fw_alloc = &tcp_memory_per_cpu_fw_alloc, + .memory_pressure = &tcp_memory_pressure, .orphan_count = &tcp_orphan_count, .sysctl_mem = sysctl_tcp_mem, diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index e2f2e087a753..16c176e7c69a 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1735,7 +1735,10 @@ struct proto udpv6_prot = { #ifdef CONFIG_BPF_SYSCALL .psock_update_sk_prot = udp_bpf_update_proto, #endif + .memory_allocated = &udp_memory_allocated, + .per_cpu_fw_alloc = &udp_memory_per_cpu_fw_alloc, + .sysctl_mem = sysctl_udp_mem, .sysctl_wmem_offset = offsetof(struct net, ipv4.sysctl_udp_wmem_min), .sysctl_rmem_offset = offsetof(struct net, ipv4.sysctl_udp_rmem_min), diff --git a/net/ipv6/udplite.c b/net/ipv6/udplite.c index fbb700d3f437..b70725856259 100644 --- a/net/ipv6/udplite.c +++ b/net/ipv6/udplite.c @@ -48,7 +48,10 @@ struct proto udplitev6_prot = { .unhash = udp_lib_unhash, .rehash = udp_v6_rehash, .get_port = udp_v6_get_port, + .memory_allocated = &udp_memory_allocated, + .per_cpu_fw_alloc = &udp_memory_per_cpu_fw_alloc, + .sysctl_mem = sysctl_udp_mem, .obj_size = sizeof(struct udp6_sock), .h.udp_table = &udplite_table, diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index e64e427a51cf..4a4b0e49ec92 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -73,11 +73,11 @@ static int xfrm6_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, struct rt6_info *rt = (struct rt6_info *)xdst->route; xdst->u.dst.dev = dev; - dev_hold_track(dev, &xdst->u.dst.dev_tracker, GFP_ATOMIC); + netdev_hold(dev, &xdst->u.dst.dev_tracker, GFP_ATOMIC); xdst->u.rt6.rt6i_idev = in6_dev_get(dev); if (!xdst->u.rt6.rt6i_idev) { - dev_put_track(dev, &xdst->u.dst.dev_tracker); + netdev_put(dev, &xdst->u.dst.dev_tracker); return -ENODEV; } |