Merge tag 'net-next-5.13' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from Jakub Kicinski:
 "Core:

   - bpf:
        - allow bpf programs calling kernel functions (initially to
          reuse TCP congestion control implementations)
        - enable task local storage for tracing programs - remove the
          need to store per-task state in hash maps, and allow tracing
          programs access to task local storage previously added for
          BPF_LSM
        - add bpf_for_each_map_elem() helper, allowing programs to walk
          all map elements in a more robust and easier to verify fashion
        - sockmap: support UDP and cross-protocol BPF_SK_SKB_VERDICT
          redirection
        - lpm: add support for batched ops in LPM trie
        - add BTF_KIND_FLOAT support - mostly to allow use of BTF on
          s390 which has floats in its headers files
        - improve BPF syscall documentation and extend the use of kdoc
          parsing scripts we already employ for bpf-helpers
        - libbpf, bpftool: support static linking of BPF ELF files
        - improve support for encapsulation of L2 packets

   - xdp: restructure redirect actions to avoid a runtime lookup,
     improving performance by 4-8% in microbenchmarks

   - xsk: build skb by page (aka generic zerocopy xmit) - improve
     performance of software AF_XDP path by 33% for devices which don't
     need headers in the linear skb part (e.g. virtio)

   - nexthop: resilient next-hop groups - improve path stability on
     next-hops group changes (incl. offload for mlxsw)

   - ipv6: segment routing: add support for IPv4 decapsulation

   - icmp: add support for RFC 8335 extended PROBE messages

   - inet: use bigger hash table for IP ID generation

   - tcp: deal better with delayed TX completions - make sure we don't
     give up on fast TCP retransmissions only because driver is slow in
     reporting that it completed transmitting the original

   - tcp: reorder tcp_congestion_ops for better cache locality

   - mptcp:
        - add sockopt support for common TCP options
        - add support for common TCP msg flags
        - include multiple address ids in RM_ADDR
        - add reset option support for resetting one subflow

   - udp: GRO L4 improvements - improve 'forward' / 'frag_list'
     co-existence with UDP tunnel GRO, allowing the first to take place
     correctly even for encapsulated UDP traffic

   - micro-optimize dev_gro_receive() and flow dissection, avoid
     retpoline overhead on VLAN and TEB GRO

   - use less memory for sysctls, add a new sysctl type, to allow using
     u8 instead of "int" and "long" and shrink networking sysctls

   - veth: allow GRO without XDP - this allows aggregating UDP packets
     before handing them off to routing, bridge, OvS, etc.

   - allow specifing ifindex when device is moved to another namespace

   - netfilter:
        - nft_socket: add support for cgroupsv2
        - nftables: add catch-all set element - special element used to
          define a default action in case normal lookup missed
        - use net_generic infra in many modules to avoid allocating
          per-ns memory unnecessarily

   - xps: improve the xps handling to avoid potential out-of-bound
     accesses and use-after-free when XPS change race with other
     re-configuration under traffic

   - add a config knob to turn off per-cpu netdev refcnt to catch
     underflows in testing

  Device APIs:

   - add WWAN subsystem to organize the WWAN interfaces better and
     hopefully start driving towards more unified and vendor-
     independent APIs

   - ethtool:
        - add interface for reading IEEE MIB stats (incl. mlx5 and bnxt
          support)
        - allow network drivers to dump arbitrary SFP EEPROM data,
          current offset+length API was a poor fit for modern SFP which
          define EEPROM in terms of pages (incl. mlx5 support)

   - act_police, flow_offload: add support for packet-per-second
     policing (incl. offload for nfp)

   - psample: add additional metadata attributes like transit delay for
     packets sampled from switch HW (and corresponding egress and
     policy-based sampling in the mlxsw driver)

   - dsa: improve support for sandwiched LAGs with bridge and DSA

   - netfilter:
        - flowtable: use direct xmit in topologies with IP forwarding,
          bridging, vlans etc.
        - nftables: counter hardware offload support

   - Bluetooth:
        - improvements for firmware download w/ Intel devices
        - add support for reading AOSP vendor capabilities
        - add support for virtio transport driver

   - mac80211:
        - allow concurrent monitor iface and ethernet rx decap
        - set priority and queue mapping for injected frames

   - phy: add support for Clause-45 PHY Loopback

   - pci/iov: add sysfs MSI-X vector assignment interface to distribute
     MSI-X resources to VFs (incl. mlx5 support)

  New hardware/drivers:

   - dsa: mv88e6xxx: add support for Marvell mv88e6393x - 11-port
     Ethernet switch with 8x 1-Gigabit Ethernet and 3x 10-Gigabit
     interfaces.

   - dsa: support for legacy Broadcom tags used on BCM5325, BCM5365 and
     BCM63xx switches

   - Microchip KSZ8863 and KSZ8873; 3x 10/100Mbps Ethernet switches

   - ath11k: support for QCN9074 a 802.11ax device

   - Bluetooth: Broadcom BCM4330 and BMC4334

   - phy: Marvell 88X2222 transceiver support

   - mdio: add BCM6368 MDIO mux bus controller

   - r8152: support RTL8153 and RTL8156 (USB Ethernet) chips

   - mana: driver for Microsoft Azure Network Adapter (MANA)

   - Actions Semi Owl Ethernet MAC

   - can: driver for ETAS ES58X CAN/USB interfaces

  Pure driver changes:

   - add XDP support to: enetc, igc, stmmac

   - add AF_XDP support to: stmmac

   - virtio:
        - page_to_skb() use build_skb when there's sufficient tailroom
          (21% improvement for 1000B UDP frames)
        - support XDP even without dedicated Tx queues - share the Tx
          queues with the stack when necessary

   - mlx5:
        - flow rules: add support for mirroring with conntrack, matching
          on ICMP, GTP, flex filters and more
        - support packet sampling with flow offloads
        - persist uplink representor netdev across eswitch mode changes
        - allow coexistence of CQE compression and HW time-stamping
        - add ethtool extended link error state reporting

   - ice, iavf: support flow filters, UDP Segmentation Offload

   - dpaa2-switch:
        - move the driver out of staging
        - add spanning tree (STP) support
        - add rx copybreak support
        - add tc flower hardware offload on ingress traffic

   - ionic:
        - implement Rx page reuse
        - support HW PTP time-stamping

   - octeon: support TC hardware offloads - flower matching on ingress
     and egress ratelimitting.

   - stmmac:
        - add RX frame steering based on VLAN priority in tc flower
        - support frame preemption (FPE)
        - intel: add cross time-stamping freq difference adjustment

   - ocelot:
        - support forwarding of MRP frames in HW
        - support multiple bridges
        - support PTP Sync one-step timestamping

   - dsa: mv88e6xxx, dpaa2-switch: offload bridge port flags like
     learning, flooding etc.

   - ipa: add IPA v4.5, v4.9 and v4.11 support (Qualcomm SDX55, SM8350,
     SC7280 SoCs)

   - mt7601u: enable TDLS support

   - mt76:
        - add support for 802.3 rx frames (mt7915/mt7615)
        - mt7915 flash pre-calibration support
        - mt7921/mt7663 runtime power management fixes"

* tag 'net-next-5.13' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2451 commits)
  net: selftest: fix build issue if INET is disabled
  net: netrom: nr_in: Remove redundant assignment to ns
  net: tun: Remove redundant assignment to ret
  net: phy: marvell: add downshift support for M88E1240
  net: dsa: ksz: Make reg_mib_cnt a u8 as it never exceeds 255
  net/sched: act_ct: Remove redundant ct get and check
  icmp: standardize naming of RFC 8335 PROBE constants
  bpf, selftests: Update array map tests for per-cpu batched ops
  bpf: Add batched ops support for percpu array
  bpf: Implement formatted output helpers with bstr_printf
  seq_file: Add a seq_bprintf function
  sfc: adjust efx->xdp_tx_queue_count with the real number of initialized queues
  net:nfc:digital: Fix a double free in digital_tg_recv_dep_req
  net: fix a concurrency bug in l2tp_tunnel_register()
  net/smc: Remove redundant assignment to rc
  mpls: Remove redundant assignment to err
  llc2: Remove redundant assignment to rc
  net/tls: Remove redundant initialization of record
  rds: Remove redundant assignment to nr_sig
  dt-bindings: net: mdio-gpio: add compatible for microchip,mdio-smi0
  ...

1 files changed, 36 insertions, 32 deletions

diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index c129ad334eb3..a0108415275f 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -15,28 +15,13 @@
 #include <linux/errno.h>
 #include <linux/types.h>
 #include <linux/string.h>
-#include <linux/socket.h>
-#include <linux/sockios.h>
-#include <linux/jiffies.h>
 #include <linux/net.h>
-#include <linux/list.h>
 #include <linux/netdevice.h>
-#include <linux/in6.h>
 #include <linux/ipv6.h>
-#include <linux/icmpv6.h>
-#include <linux/random.h>
 #include <linux/slab.h>
 
-#include <net/sock.h>
-#include <net/snmp.h>
 #include <net/ipv6_frag.h>
 
-#include <net/protocol.h>
-#include <net/transp_v6.h>
-#include <net/rawv6.h>
-#include <net/ndisc.h>
-#include <net/addrconf.h>
-#include <net/inet_ecn.h>
 #include <net/netfilter/ipv6/nf_conntrack_ipv6.h>
 #include <linux/sysctl.h>
 #include <linux/netfilter.h>
@@ -44,11 +29,18 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <net/netfilter/ipv6/nf_defrag_ipv6.h>
+#include <net/netns/generic.h>
 
 static const char nf_frags_cache_name[] = "nf-frags";
 
+unsigned int nf_frag_pernet_id __read_mostly;
 static struct inet_frags nf_frags;
 
+static struct nft_ct_frag6_pernet *nf_frag_pernet(struct net *net)
+{
+	return net_generic(net, nf_frag_pernet_id);
+}
+
 #ifdef CONFIG_SYSCTL
 
 static struct ctl_table nf_ct_frag6_sysctl_table[] = {
@@ -75,6 +67,7 @@ static struct ctl_table nf_ct_frag6_sysctl_table[] = {
 
 static int nf_ct_frag6_sysctl_register(struct net *net)
 {
+	struct nft_ct_frag6_pernet *nf_frag;
 	struct ctl_table *table;
 	struct ctl_table_header *hdr;
 
@@ -86,18 +79,20 @@ static int nf_ct_frag6_sysctl_register(struct net *net)
 			goto err_alloc;
 	}
 
-	table[0].data	= &net->nf_frag.fqdir->timeout;
-	table[1].data	= &net->nf_frag.fqdir->low_thresh;
-	table[1].extra2	= &net->nf_frag.fqdir->high_thresh;
-	table[2].data	= &net->nf_frag.fqdir->high_thresh;
-	table[2].extra1	= &net->nf_frag.fqdir->low_thresh;
-	table[2].extra2	= &init_net.nf_frag.fqdir->high_thresh;
+	nf_frag = nf_frag_pernet(net);
+
+	table[0].data	= &nf_frag->fqdir->timeout;
+	table[1].data	= &nf_frag->fqdir->low_thresh;
+	table[1].extra2	= &nf_frag->fqdir->high_thresh;
+	table[2].data	= &nf_frag->fqdir->high_thresh;
+	table[2].extra1	= &nf_frag->fqdir->low_thresh;
+	table[2].extra2	= &nf_frag->fqdir->high_thresh;
 
 	hdr = register_net_sysctl(net, "net/netfilter", table);
 	if (hdr == NULL)
 		goto err_reg;
 
-	net->nf_frag_frags_hdr = hdr;
+	nf_frag->nf_frag_frags_hdr = hdr;
 	return 0;
 
 err_reg:
@@ -109,10 +104,11 @@ err_alloc:
 
 static void __net_exit nf_ct_frags6_sysctl_unregister(struct net *net)
 {
+	struct nft_ct_frag6_pernet *nf_frag = nf_frag_pernet(net);
 	struct ctl_table *table;
 
-	table = net->nf_frag_frags_hdr->ctl_table_arg;
-	unregister_net_sysctl_table(net->nf_frag_frags_hdr);
+	table = nf_frag->nf_frag_frags_hdr->ctl_table_arg;
+	unregister_net_sysctl_table(nf_frag->nf_frag_frags_hdr);
 	if (!net_eq(net, &init_net))
 		kfree(table);
 }
@@ -149,6 +145,7 @@ static void nf_ct_frag6_expire(struct timer_list *t)
 static struct frag_queue *fq_find(struct net *net, __be32 id, u32 user,
 				  const struct ipv6hdr *hdr, int iif)
 {
+	struct nft_ct_frag6_pernet *nf_frag = nf_frag_pernet(net);
 	struct frag_v6_compare_key key = {
 		.id = id,
 		.saddr = hdr->saddr,
@@ -158,7 +155,7 @@ static struct frag_queue *fq_find(struct net *net, __be32 id, u32 user,
 	};
 	struct inet_frag_queue *q;
 
-	q = inet_frag_find(net->nf_frag.fqdir, &key);
+	q = inet_frag_find(nf_frag->fqdir, &key);
 	if (!q)
 		return NULL;
 
@@ -495,37 +492,44 @@ EXPORT_SYMBOL_GPL(nf_ct_frag6_gather);
 
 static int nf_ct_net_init(struct net *net)
 {
+	struct nft_ct_frag6_pernet *nf_frag  = nf_frag_pernet(net);
 	int res;
 
-	res = fqdir_init(&net->nf_frag.fqdir, &nf_frags, net);
+	res = fqdir_init(&nf_frag->fqdir, &nf_frags, net);
 	if (res < 0)
 		return res;
 
-	net->nf_frag.fqdir->high_thresh = IPV6_FRAG_HIGH_THRESH;
-	net->nf_frag.fqdir->low_thresh = IPV6_FRAG_LOW_THRESH;
-	net->nf_frag.fqdir->timeout = IPV6_FRAG_TIMEOUT;
+	nf_frag->fqdir->high_thresh = IPV6_FRAG_HIGH_THRESH;
+	nf_frag->fqdir->low_thresh = IPV6_FRAG_LOW_THRESH;
+	nf_frag->fqdir->timeout = IPV6_FRAG_TIMEOUT;
 
 	res = nf_ct_frag6_sysctl_register(net);
 	if (res < 0)
-		fqdir_exit(net->nf_frag.fqdir);
+		fqdir_exit(nf_frag->fqdir);
 	return res;
 }
 
 static void nf_ct_net_pre_exit(struct net *net)
 {
-	fqdir_pre_exit(net->nf_frag.fqdir);
+	struct nft_ct_frag6_pernet *nf_frag  = nf_frag_pernet(net);
+
+	fqdir_pre_exit(nf_frag->fqdir);
 }
 
 static void nf_ct_net_exit(struct net *net)
 {
+	struct nft_ct_frag6_pernet *nf_frag  = nf_frag_pernet(net);
+
 	nf_ct_frags6_sysctl_unregister(net);
-	fqdir_exit(net->nf_frag.fqdir);
+	fqdir_exit(nf_frag->fqdir);
 }
 
 static struct pernet_operations nf_ct_net_ops = {
 	.init		= nf_ct_net_init,
 	.pre_exit	= nf_ct_net_pre_exit,
 	.exit		= nf_ct_net_exit,
+	.id		= &nf_frag_pernet_id,
+	.size		= sizeof(struct nft_ct_frag6_pernet),
 };
 
 static const struct rhashtable_params nfct_rhash_params = {