Before freeing the hash table in addrconf_exit_net(),
we need to make sure the work queue has completed,
or risk NULL dereference or UAF.
Thus, use cancel_delayed_work_sync() to enforce this.
We do not hold RTNL in addrconf_exit_net(), making this safe.
Fixes: 8805d13ff1 ("ipv6/addrconf: use one delayed work per netns")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/r/20220216182037.3742-1-eric.dumazet@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Support setting IPV6_HOPLIMIT, IPV6_TCLASS, IPV6_DONTFRAG
during sendmsg via SOL_IPV6 cmsgs.
tclass and dontfrag are init'ed from struct ipv6_pinfo in
ipcm6_init_sk(), while hlimit is inited to -1, so we need
to handle it being populated via cmsg explicitly.
Leave extension headers and flowlabel unimplemented.
Those are slightly more laborious to test and users
seem to primarily care about IPV6_TCLASS.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Ipv6 flowlabels historically require a reservation before use.
Optionally in exclusive mode (e.g., user-private).
Commit 59c820b231 ("ipv6: elide flowlabel check if no exclusive
leases exist") introduced a fastpath that avoids this check when no
exclusive leases exist in the system, and thus any flowlabel use
will be granted.
That allows skipping the control operation to reserve a flowlabel
entirely. Though with a warning if the fast path fails:
This is an optimization. Robust applications still have to revert to
requesting leases if the fast path fails due to an exclusive lease.
Still, this is subtle. Better isolate network namespaces from each
other. Flowlabels are per-netns. Also record per-netns whether
exclusive leases are in use. Then behavior does not change based on
activity in other netns.
Changes
v2
- wrap in IS_ENABLED(CONFIG_IPV6) to avoid breakage if disabled
Fixes: 59c820b231 ("ipv6: elide flowlabel check if no exclusive leases exist")
Link: https://lore.kernel.org/netdev/MWHPR2201MB1072BCCCFCE779E4094837ACD0329@MWHPR2201MB1072.namprd22.prod.outlook.com/
Reported-by: Congyu Liu <liu3101@purdue.edu>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Tested-by: Congyu Liu <liu3101@purdue.edu>
Link: https://lore.kernel.org/r/20220215160037.1976072-1-willemdebruijn.kernel@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Whenever rt6_uncached_list_flush_dev() swaps rt->rt6_idev
to the blackhole device, parts of IPv6 stack might still need
to increment one SNMP counter.
Root cause, patch from Ido, changelog from Eric :)
This bug suggests that we need to audit rt->rt6_idev usages
and make sure they are properly using RCU protection.
Fixes: e5f80fcf86 ("ipv6: give an IPv6 dev to blackhole_netdev")
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add reasons to __udp6_lib_rcv for skb drops. The only twist is that the
NO_SOCKET takes precedence over the CSUM or other counters for that
path (motivation behind this patch - csum counter was misleading).
Signed-off-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Generate RTM_NEWROUTE netlink notification when the route preference
changes on an existing kernel generated default route in response to
RA messages. Currently netlink notifications are generated only when
this route is added or deleted but not when the route preference
changes, which can cause userspace routing application state to go
out of sync with kernel.
Signed-off-by: Kalash Nainwal <kalash@arista.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
This is an optimization to keep the per-cpu lists as short as possible:
Whenever rt6_uncached_list_flush_dev() changes one rt6_info
matching the disappearing device, it can can transfer the object
to a quarantine list, waiting for a final rt6_uncached_list_del().
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
IPv6 addrconf notifiers wants the loopback device to
be the last device being dismantled at netns deletion.
This caused many limitations and work arounds.
Back in linux-5.3, Mahesh added a per host blackhole_netdev
that can be used whenever we need to make sure objects no longer
refer to a disappearing device.
If we attach to blackhole_netdev an ip6_ptr (allocate an idev),
then we can use this special device (which is never freed)
in place of the loopback_dev (which can be freed).
This will permit improvements in netdev_run_todo() and other parts
of the stack where had steps to make sure loopback_dev was
the last device to disappear.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Mahesh Bandewar <maheshb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This counter has never been visible, there is little point
trying to maintain it.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The ->rtm_tos option is normally used to route packets based on both
the destination address and the DS field. However it's ignored for
IPv6 routes. Setting ->rtm_tos for IPv6 is thus invalid as the route
is going to work only on the destination address anyway, so it won't
behave as specified.
Suggested-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: Guillaume Nault <gnault@redhat.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Reviewed-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Minor reordering of the code and a call to sock_cmsg_send()
gives us support for setting the common socket options via
cmsg (the usual ones - SO_MARK, SO_TIMESTAMPING_OLD, SCM_TXTIME).
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Nothing prevents the user from requesting timestamping
on ping6 sockets, yet timestamps are not going to be reported.
Plumb the flags through.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
We have ftrace and BPF today, there's no need for printing arguments
at the start of a function.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Commit
9652dc2eb9 ("tcp: relax listening_hash operations")
removed the need to disable bottom half while acquiring
listening_hash.lock. There are still two callers left which disable
bottom half before the lock is acquired.
On PREEMPT_RT the softirqs are preemptible and local_bh_disable() acts
as a lock to ensure that resources, that are protected by disabling
bottom halves, remain protected.
This leads to a circular locking dependency if the lock acquired with
disabled bottom halves is also acquired with enabled bottom halves
followed by disabling bottom halves. This is the reverse locking order.
It has been observed with inet_listen_hashbucket:🔒
local_bh_disable() + spin_lock(&ilb->lock):
inet_listen()
inet_csk_listen_start()
sk->sk_prot->hash() := inet_hash()
local_bh_disable()
__inet_hash()
spin_lock(&ilb->lock);
acquire(&ilb->lock);
Reverse order: spin_lock(&ilb2->lock) + local_bh_disable():
tcp_seq_next()
listening_get_next()
spin_lock(&ilb2->lock);
acquire(&ilb2->lock);
tcp4_seq_show()
get_tcp4_sock()
sock_i_ino()
read_lock_bh(&sk->sk_callback_lock);
acquire(softirq_ctrl) // <---- whoops
acquire(&sk->sk_callback_lock)
Drop local_bh_disable() around __inet_hash() which acquires
listening_hash->lock. Split inet_unhash() and acquire the
listen_hashbucket lock without disabling bottom halves; the inet_ehash
lock with disabled bottom halves.
Reported-by: Mike Galbraith <efault@gmx.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Link: https://lkml.kernel.org/r/12d6f9879a97cd56c09fb53dee343cbb14f7f1f7.camel@gmx.de
Link: https://lkml.kernel.org/r/X9CheYjuXWc75Spa@hirez.programming.kicks-ass.net
Link: https://lore.kernel.org/r/YgQOebeZ10eNx1W6@linutronix.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
cleanup_net() is competing with other rtnl users.
Avoiding to acquire rtnl for each netns before calling
ip6mr_rules_exit() gives chance for cleanup_net()
to progress much faster, holding rtnl a bit longer.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
cleanup_net() is competing with other rtnl users.
fib6_rules_net_exit() seems a good candidate for exit_batch(),
as this gives chance for cleanup_net() to progress much faster,
holding rtnl a bit longer.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
IPv6 does not scale very well with the number of IPv6 addresses.
It uses a global (shared by all netns) hash table with 256 buckets.
Some functions like addrconf_verify_rtnl() and addrconf_ifdown()
have to iterate all addresses in the hash table.
I have seen addrconf_verify_rtnl() holding the cpu for 10ms or more.
Switch to the per netns hashtable (and spinlock) added
in prior patches.
This considerably speeds up netns dismantle times on hosts
with thousands of netns. This also has an impact
on regular (fast path) IPv6 processing.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Next step for using per netns inet6_addr_lst
is to have per netns work item to ultimately
call addrconf_verify_rtnl() and addrconf_verify()
with a new 'struct net*' argument.
Everything is still using the global inet6_addr_lst[] table.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Add a per netns hash table and a dedicated spinlock,
first step to get rid of the global inet6_addr_lst[] one.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Define a dscp_t type and its appropriate helpers that ensure ECN bits
are not taken into account when handling DSCP.
Use this new type to replace the tclass field of struct fib6_rule, so
that fib6-rules don't get influenced by ECN bits anymore.
Before this patch, fib6-rules didn't make any distinction between the
DSCP and ECN bits. Therefore, rules specifying a DSCP (tos or dsfield
options in iproute2) stopped working as soon a packets had at least one
of its ECN bits set (as a work around one could create four rules for
each DSCP value to match, one for each possible ECN value).
After this patch fib6-rules only compare the DSCP bits. ECN doesn't
influence the result anymore. Also, fib6-rules now must have the ECN
bits cleared or they will be rejected.
Signed-off-by: Guillaume Nault <gnault@redhat.com>
Acked-by: David Ahern <dsahern@kernel.org>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
In many cases, ip6mr_sk_done() is called while no ipmr socket
has been registered.
This removes 4 rtnl acquisitions per netns dismantle,
with following callers:
igmp6_net_exit(), tcpv6_net_exit(), ndisc_net_exit()
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This fixes minor data-races in ip6_mc_input() and
batadv_mcast_mla_rtr_flags_softif_get_ipv6()
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add support for the IOAM insertion frequency inside its lwtunnel output
function. This patch introduces a new (atomic) counter for packets,
based on which the algorithm will decide if IOAM should be added or not.
Default frequency is "1/1" (i.e., applied to all packets) for backward
compatibility. The iproute2 patch is ready and will be submitted as soon
as this one is accepted.
Previous iproute2 command:
ip -6 ro ad fc00::1/128 encap ioam6 [ mode ... ] ...
New iproute2 command:
ip -6 ro ad fc00::1/128 encap ioam6 [ freq k/n ] [ mode ... ] ...
Signed-off-by: Justin Iurman <justin.iurman@uliege.be>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Inline a part of ipv6_fixup_options() to avoid extra overhead on
function call if opt is NULL.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
udpv6_sendmsg() doesn't need dst after calling ip6_make_skb(), so
instead of taking an additional reference inside ip6_setup_cork()
and releasing the initial one afterwards, we can hand over a reference
into ip6_make_skb() saving two atomics. The only other user of
ip6_setup_cork() is ip6_append_data() and it requires an extra
dst_hold().
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
udpv6_sendmsg() first initialises an on-stack 88B struct flowi6 and then
copies it into cork, which is expensive. Avoid the copy in corkless case
by initialising on-stack cork->fl directly.
The main part is a couple of lines under !corkreq check. The rest
converts fl6 variable to be a pointer.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Another preparation patch. inet_cork_full already contains a field for
iflow, so we can avoid passing a separate struct iflow6 into
__ip6_append_data() and ip6_make_skb(), and use the flow stored in
inet_cork_full. Make sure callers set cork->fl, i.e. we init it in
ip6_append_data() and before calling ip6_make_skb().
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Convert a struct inet_cork argument in __ip6_append_data() to struct
inet_cork_full. As one struct contains another inet_cork is still can
be accessed via ->base field. It's a preparation patch making further
changes a bit cleaner.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
It doesn't appear there is any reason for ip6_cork_release() to zero
cork->fl, it'll be fully filled on next initialisation. This 88 bytes
memset accounts to 0.3-0.5% of total CPU cycles.
It's also needed in following patches and allows to remove an extar flow
copy in udp_v6_push_pending_frames().
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Clean up ip6_setup_cork() and ip6_cork_release() adding a local variable
for v6_cork->opt. It's a preparation patch for further changes.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
ipv6_push_nfrag_opts() doesn't change passed daddr, and so
__ip6_make_skb() doesn't actually need to keep an on-stack copy of
fl6->daddr. Set initially final_dst to fl6->daddr,
ipv6_push_nfrag_opts() will override it if needed, and get rid of extra
copies.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Corked AF_INET for ipv6 socket doesn't appear to be the hottest case,
so move it out of the common path under up->pending check to remove
overhead.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
__ip6_make_skb() gets a cork->dst ref, hands it over to skb and shortly
after puts cork->dst. Save two atomics by stealing it without extra
referencing, ip6_cork_release() handles NULL cork->dst.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Pablo Neira Ayuso says:
====================
Netfilter fixes for net
1) Remove leftovers from flowtable modules, from Geert Uytterhoeven.
2) Missing refcount increment of conntrack template in nft_ct,
from Florian Westphal.
3) Reduce nft_zone selftest time, also from Florian.
4) Add selftest to cover stateless NAT on fragments, from Florian Westphal.
5) Do not set net_device when for reject packets from the bridge path,
from Phil Sutter.
6) Cancel register tracking info on nft_byteorder operations.
7) Extend nft_concat_range selftest to cover set reload with no elements,
from Florian Westphal.
8) Remove useless update of pointer in chain blob builder, reported
by kbuild test robot.
* git://git.kernel.org/pub/scm/linux/kernel/git/pablo/nf:
netfilter: nf_tables: remove assignment with no effect in chain blob builder
selftests: nft_concat_range: add test for reload with no element add/del
netfilter: nft_byteorder: track register operations
netfilter: nft_reject_bridge: Fix for missing reply from prerouting
selftests: netfilter: check stateless nat udp checksum fixup
selftests: netfilter: reduce zone stress test running time
netfilter: nft_ct: fix use after free when attaching zone template
netfilter: Remove flowtable relics
====================
Link: https://lore.kernel.org/r/20220127235235.656931-1-pablo@netfilter.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
This reverts commit b75326c201.
This commit breaks Linux compatibility with USGv6 tests. The RFC this
commit was based on is actually an expired draft: no published RFC
currently allows the new behaviour it introduced.
Without full IETF endorsement, the flash renumbering scenario this
patch was supposed to enable is never going to work, as other IPv6
equipements on the same LAN will keep the 2 hours limit.
Fixes: b75326c201 ("ipv6: Honor all IPv6 PIO Valid Lifetime values")
Signed-off-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
NF_FLOW_TABLE_IPV4 and NF_FLOW_TABLE_IPV6 are invisble, selected by
nothing (so they can no longer be enabled), and their last real users
have been removed (nf_flow_table_ipv6.c is empty).
Clean up the leftovers.
Fixes: c42ba4290b ("netfilter: flowtable: remove ipv4/ipv6 modules")
Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
IPv6 GRO considers packets to belong to different flows when their
hop_limit is different. This seems counter-intuitive, the flow is
the same. hop_limit may vary because of various bugs or hacks but
that doesn't mean it's okay for GRO to reorder packets.
Practical impact of this problem on overall TCP performance
is unclear, but TCP itself detects this reordering and bumps
TCPSACKReorder resulting in user complaints.
Eric warns that there may be performance regressions in setups
which do packet spraying across links with similar RTT but different
hop count. To be safe let's target -next and not treat this
as a fix. If the packet spraying is using flow label there should
be no difference in behavior as flow label is checked first.
Note that the code plays an easy to miss trick by upcasting next_hdr
to a u16 pointer and compares next_hdr and hop_limit in one go.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Back in linux-2.6.25 (commit 98c6d1b261 "[NETNS]: Make icmpv6_sk per namespace.",
we added private per-cpu/per-netns ipv6 icmp sockets.
This adds memory and cpu costs, which do not seem needed.
Now typical servers have 256 or more cores, this adds considerable
tax to netns users.
icmp sockets are used from BH context, are not receiving packets,
and do not store any persistent state but the 'struct net' pointer.
icmpv6_xmit_lock() already makes sure to lock the chosen per-cpu
socket.
This patch has a considerable impact on the number of netns
that the worker thread in cleanup_net() can dismantle per second,
because ip6mr_sk_done() is no longer called, meaning we no longer
acquire the rtnl mutex, competing with other threads adding new netns.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Prior patches in the series made sure tw_timer_handler()
can be fired after netns has been dismantled/freed.
We no longer have to scan a potentially big TCP ehash
table at netns dismantle.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Since IPv4 routes support IPv6 gateways now, we can route IPv4 traffic in
NBMA tunnels.
Signed-off-by: Qing Deng <i@moy.cat>
Signed-off-by: David S. Miller <davem@davemloft.net>
