kernel/linux.git/include/net/ipv6.h, branch v4.19.302

tcp: Reduce chance of collisions in inet6_hashfn().

2023-08-11T09:45:31+00:00

[ Upstream commit d11b0df7ddf1831f3e170972f43186dad520bfcc ] For both IPv4 and IPv6 incoming TCP connections are tracked in a hash table with a hash over the source & destination addresses and ports. However, the IPv6 hash is insufficient and can lead to a high rate of collisions. The IPv6 hash used an XOR to fit everything into the 96 bits for the fast jenkins hash, meaning it is possible for an external entity to ensure the hash collides, thus falling back to a linear search in the bucket, which is slow. We take the approach of hash the full length of IPv6 address in __ipv6_addr_jhash() so that all users can benefit from a more secure version. While this may look like it adds overhead, the reality of modern CPUs means that this is unmeasurable in real world scenarios. In simulating with llvm-mca, the increase in cycles for the hashing code was ~16 cycles on Skylake (from a base of ~155), and an extra ~9 on Nehalem (base of ~173). In commit dd6d2910c5e0 ("netfilter: conntrack: switch to siphash") netfilter switched from a jenkins hash to a siphash, but even the faster hsiphash is a more significant overhead (~20-30%) in some preliminary testing. So, in this patch, we keep to the more conservative approach to ensure we don't add much overhead per SYN. In testing, this results in a consistently even spread across the connection buckets. In both testing and real-world scenarios, we have not found any measurable performance impact. Fixes: 08dcdbf6a7b9 ("ipv6: use a stronger hash for tcp") Signed-off-by: Stewart Smith Signed-off-by: Samuel Mendoza-Jonas Suggested-by: Eric Dumazet Signed-off-by: Kuniyuki Iwashima Reviewed-by: Eric Dumazet Link: https://lore.kernel.org/r/20230721222410.17914-1-kuniyu@amazon.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin

tcp/udp: Call inet6_destroy_sock() in IPv6 sk->sk_destruct().

2023-04-26T09:21:52+00:00

commit d38afeec26ed4739c640bf286c270559aab2ba5f upstream. Originally, inet6_sk(sk)->XXX were changed under lock_sock(), so we were able to clean them up by calling inet6_destroy_sock() during the IPv6 -> IPv4 conversion by IPV6_ADDRFORM. However, commit 03485f2adcde ("udpv6: Add lockless sendmsg() support") added a lockless memory allocation path, which could cause a memory leak: setsockopt(IPV6_ADDRFORM) sendmsg() +-----------------------+ +-------+ - do_ipv6_setsockopt(sk, ...) - udpv6_sendmsg(sk, ...) - sockopt_lock_sock(sk) ^._ called via udpv6_prot - lock_sock(sk) before WRITE_ONCE() - WRITE_ONCE(sk->sk_prot, &tcp_prot) - inet6_destroy_sock() - if (!corkreq) - sockopt_release_sock(sk) - ip6_make_skb(sk, ...) - release_sock(sk) ^._ lockless fast path for the non-corking case - __ip6_append_data(sk, ...) - ipv6_local_rxpmtu(sk, ...) - xchg(&np->rxpmtu, skb) ^._ rxpmtu is never freed. - goto out_no_dst; - lock_sock(sk) For now, rxpmtu is only the case, but not to miss the future change and a similar bug fixed in commit e27326009a3d ("net: ping6: Fix memleak in ipv6_renew_options()."), let's set a new function to IPv6 sk->sk_destruct() and call inet6_cleanup_sock() there. Since the conversion does not change sk->sk_destruct(), we can guarantee that we can clean up IPv6 resources finally. We can now remove all inet6_destroy_sock() calls from IPv6 protocol specific ->destroy() functions, but such changes are invasive to backport. So they can be posted as a follow-up later for net-next. Fixes: 03485f2adcde ("udpv6: Add lockless sendmsg() support") Signed-off-by: Kuniyuki Iwashima Signed-off-by: Jakub Kicinski Signed-off-by: Ziyang Xuan Signed-off-by: Greg Kroah-Hartman

udp: Call inet6_destroy_sock() in setsockopt(IPV6_ADDRFORM).

2023-04-26T09:21:52+00:00

commit 21985f43376cee092702d6cb963ff97a9d2ede68 upstream. Commit 4b340ae20d0e ("IPv6: Complete IPV6_DONTFRAG support") forgot to add a change to free inet6_sk(sk)->rxpmtu while converting an IPv6 socket into IPv4 with IPV6_ADDRFORM. After conversion, sk_prot is changed to udp_prot and ->destroy() never cleans it up, resulting in a memory leak. This is due to the discrepancy between inet6_destroy_sock() and IPV6_ADDRFORM, so let's call inet6_destroy_sock() from IPV6_ADDRFORM to remove the difference. However, this is not enough for now because rxpmtu can be changed without lock_sock() after commit 03485f2adcde ("udpv6: Add lockless sendmsg() support"). We will fix this case in the following patch. Note we will rename inet6_destroy_sock() to inet6_cleanup_sock() and remove unnecessary inet6_destroy_sock() calls in sk_prot->destroy() in the future. Fixes: 4b340ae20d0e ("IPv6: Complete IPV6_DONTFRAG support") Signed-off-by: Kuniyuki Iwashima Signed-off-by: Jakub Kicinski Signed-off-by: Ziyang Xuan Signed-off-by: Greg Kroah-Hartman

net: ipv6: add net argument to ip6_dst_lookup_flow

2020-04-29T14:31:16+00:00

commit c4e85f73afb6384123e5ef1bba3315b2e3ad031e upstream. This will be used in the conversion of ipv6_stub to ip6_dst_lookup_flow, as some modules currently pass a net argument without a socket to ip6_dst_lookup. This is equivalent to commit 343d60aada5a ("ipv6: change ipv6_stub_impl.ipv6_dst_lookup to take net argument"). Signed-off-by: Sabrina Dubroca Signed-off-by: David S. Miller [bwh: Backported to 4.19: adjust context] Signed-off-by: Ben Hutchings Signed-off-by: Sasha Levin

net: don't declare IPv6 non-local bind helper if CONFIG_IPV6 undefined

2018-08-01T20:45:31+00:00

Fixes: 83ba4645152d ("net: add helpers checking if socket can be bound to nonlocal address") Signed-off-by: Vincent Bernat Signed-off-by: David S. Miller

net: add helpers checking if socket can be bound to nonlocal address

2018-08-01T16:50:04+00:00

The construction "net->ipv4.sysctl_ip_nonlocal_bind || inet->freebind || inet->transparent" is present three times and its IPv6 counterpart is also present three times. We introduce two small helpers to characterize these tests uniformly. Signed-off-by: Vincent Bernat Signed-off-by: David S. Miller

Merge git://git.kernel.org/pub/scm/linux/kernel/git/pablo/nf-next

2018-07-21T05:28:28+00:00

Pablo Neira Ayuso says: ==================== Netfilter/IPVS updates for net-next The following patchset contains Netfilter/IPVS updates for your net-next tree: 1) No need to set ttl from reject action for the bridge family, from Taehee Yoo. 2) Use a fixed timeout for flow that are passed up from the flowtable to conntrack, from Florian Westphal. 3) More preparation patches for tproxy support for nf_tables, from Mate Eckl. 4) Remove unnecessary indirection in core IPv6 checksum function, from Florian Westphal. 5) Use nf_ct_get_tuplepr() from openvswitch, instead of opencoding it. From Florian Westphal. 6) socket match now selects socket infrastructure, instead of depending on it. From Mate Eckl. 7) Patch series to simplify conntrack tuple building/parsing from packet path and ctnetlink, from Florian Westphal. 8) Fetch timeout policy from protocol helpers, instead of doing it from core, from Florian Westphal. 9) Merge IPv4 and IPv6 protocol trackers into conntrack core, from Florian Westphal. 10) Depend on CONFIG_NF_TABLES_IPV6 and CONFIG_IP6_NF_IPTABLES respectively, instead of IPV6. Patch from Mate Eckl. 11) Add specific function for garbage collection in conncount, from Yi-Hung Wei. 12) Catch number of elements in the connlimit list, from Yi-Hung Wei. 13) Move locking to nf_conncount, from Yi-Hung Wei. 14) Series of patches to add lockless tree traversal in nf_conncount, from Yi-Hung Wei. 15) Resolve clash in matching conntracks when race happens, from Martynas Pumputis. 16) If connection entry times out, remove template entry from the ip_vs_conn_tab table to improve behaviour under flood, from Julian Anastasov. 17) Remove useless parameter from nf_ct_helper_ext_add(), from Gao feng. 18) Call abort from 2-phase commit protocol before requesting modules, make sure this is done under the mutex, from Florian Westphal. 19) Grab module reference when starting transaction, also from Florian. 20) Dynamically allocate expression info array for pre-parsing, from Florian. 21) Add per netns mutex for nf_tables, from Florian Westphal. 22) A couple of patches to simplify and refactor nf_osf code to prepare for nft_osf support. 23) Break evaluation on missing socket, from Mate Eckl. 24) Allow to match socket mark from nft_socket, from Mate Eckl. 25) Remove dependency on nf_defrag_ipv6, now that IPv6 tracker is built-in into nf_conntrack. From Florian Westphal. ==================== Signed-off-by: David S. Miller

Merge ra.kernel.org:/pub/scm/linux/kernel/git/torvalds/linux

2018-07-21T04:17:12+00:00

All conflicts were trivial overlapping changes, so reasonably easy to resolve. Signed-off-by: David S. Miller

ipv6: fix useless rol32 call on hash

2018-07-18T22:11:09+00:00

The rol32 call is currently rotating hash but the rol'd value is being discarded. I believe the current code is incorrect and hash should be assigned the rotated value returned from rol32. Thanks to David Lebrun for spotting this. Signed-off-by: Colin Ian King Signed-off-by: David S. Miller

ipv6: remove dependency of nf_defrag_ipv6 on ipv6 module

2018-07-18T09:26:53+00:00

IPV6=m DEFRAG_IPV6=m CONNTRACK=y yields: net/netfilter/nf_conntrack_proto.o: In function `nf_ct_netns_do_get': net/netfilter/nf_conntrack_proto.c:802: undefined reference to `nf_defrag_ipv6_enable' net/netfilter/nf_conntrack_proto.o:(.rodata+0x640): undefined reference to `nf_conntrack_l4proto_icmpv6' Setting DEFRAG_IPV6=y causes undefined references to ip6_rhash_params ip6_frag_init and ip6_expire_frag_queue so it would be needed to force IPV6=y too. This patch gets rid of the 'followup linker error' by removing the dependency of ipv6.ko symbols from netfilter ipv6 defrag. Shared code is placed into a header, then used from both. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso