Pablo Neira Ayuso says:
====================
Netfilter fixes for net
1) Use kfree_rcu(ptr, rcu) variant, using kfree_rcu(ptr) was not
intentional. From Eric Dumazet.
2) Use-after-free in netfilter hook core, from Eric Dumazet.
3) Missing rcu read lock side for netfilter egress hook,
from Florian Westphal.
4) nf_queue assume state->sk is full socket while it might not be.
Invoke sock_gen_put(), from Florian Westphal.
5) Add selftest to exercise the reported KASAN splat in 4)
6) Fix possible use-after-free in nf_queue in case sk_refcnt is 0.
Also from Florian.
7) Use input interface index only for hardware offload, not for
the software plane. This breaks tc ct action. Patch from Paul Blakey.
* git://git.kernel.org/pub/scm/linux/kernel/git/netfilter/nf:
net/sched: act_ct: Fix flow table lookup failure with no originating ifindex
netfilter: nf_queue: handle socket prefetch
netfilter: nf_queue: fix possible use-after-free
selftests: netfilter: add nfqueue TCP_NEW_SYN_RECV socket race test
netfilter: nf_queue: don't assume sk is full socket
netfilter: egress: silence egress hook lockdep splats
netfilter: fix use-after-free in __nf_register_net_hook()
netfilter: nf_tables: prefer kfree_rcu(ptr, rcu) variant
====================
Link: https://lore.kernel.org/r/20220301215337.378405-1-pablo@netfilter.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
After cited commit optimizted hw insertion, flow table entries are
populated with ifindex information which was intended to only be used
for HW offload. This tuple ifindex is hashed in the flow table key, so
it must be filled for lookup to be successful. But tuple ifindex is only
relevant for the netfilter flowtables (nft), so it's not filled in
act_ct flow table lookup, resulting in lookup failure, and no SW
offload and no offload teardown for TCP connection FIN/RST packets.
To fix this, add new tc ifindex field to tuple, which will
only be used for offloading, not for lookup, as it will not be
part of the tuple hash.
Fixes: 9795ded7f9 ("net/sched: act_ct: Fill offloading tuple iifidx")
Signed-off-by: Paul Blakey <paulb@nvidia.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
johannes Berg says:
====================
Some last-minute fixes:
* rfkill
- add missing rfill_soft_blocked() when disabled
* cfg80211
- handle a nla_memdup() failure correctly
- fix CONFIG_CFG80211_EXTRA_REGDB_KEYDIR typo in
Makefile
* mac80211
- fix EAPOL handling in 802.3 RX path
- reject setting up aggregation sessions before
connection is authorized to avoid timeouts or
similar
- handle some SAE authentication steps correctly
- fix AC selection in mesh forwarding
* iwlwifi
- remove TWT support as it causes firmware crashes
when the AP isn't behaving correctly
- check debugfs pointer before dereferncing it
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Send data all the way down to the RDMA device is a time
consuming operation(get a new slot, maybe do RDMA Write
and send a CDC, etc). Moving those operations from BH
to user context is good for performance.
If the sock_lock is hold by user, we don't try to send
data out in the BH context, but just mark we should
send. Since the user will release the sock_lock soon, we
can do the sending there.
Add smc_release_cb() which will be called in release_sock()
and try send in the callback if needed.
This patch moves the sending part out from BH if sock lock
is hold by user. In my testing environment, this saves about
20% softirq in the qperf 4K tcp_bw test in the sender side
with no noticeable throughput drop.
Signed-off-by: Dust Li <dust.li@linux.alibaba.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When we are handling softirq workload, enable hardirq may
again interrupt the current routine of softirq, and then
try to raise softirq again. This only wastes CPU cycles
and won't have any real gain.
Since IB_CQ_REPORT_MISSED_EVENTS already make sure if
ib_req_notify_cq() returns 0, it is safe to wait for the
next event, with no need to poll the CQ again in this case.
This patch disables hardirq during the processing of softirq,
and re-arm the CQ after softirq is done. Somehow like NAPI.
Co-developed-by: Guangguan Wang <guangguan.wang@linux.alibaba.com>
Signed-off-by: Guangguan Wang <guangguan.wang@linux.alibaba.com>
Signed-off-by: Dust Li <dust.li@linux.alibaba.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
rmbe_update_limit is used to limit announcing receive
window updating too frequently. RFC7609 request a minimal
increase in the window size of 10% of the receive buffer
space. But current implementation used:
min_t(int, rmbe_size / 10, SOCK_MIN_SNDBUF / 2)
and SOCK_MIN_SNDBUF / 2 == 2304 Bytes, which is almost
always less then 10% of the receive buffer space.
This causes the receiver always sending CDC message to
update its consumer cursor when it consumes more then 2K
of data. And as a result, we may encounter something like
"TCP silly window syndrome" when sending 2.5~8K message.
This patch fixes this using max(rmbe_size / 10, SOCK_MIN_SNDBUF / 2).
With this patch and SMC autocorking enabled, qperf 2K/4K/8K
tcp_bw test shows 45%/75%/40% increase in throughput respectively.
Signed-off-by: Dust Li <dust.li@linux.alibaba.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In commit ea785a1a573b("net/smc: Send directly when
TCP_CORK is cleared"), we don't use delayed work
to implement cork.
This patch use the same algorithm, removes the
delayed work when setting TCP_NODELAY and send
directly in setsockopt(). This also makes the
TCP_NODELAY the same as TCP.
Cc: Tony Lu <tonylu@linux.alibaba.com>
Signed-off-by: Dust Li <dust.li@linux.alibaba.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This add a new sysctl: net.smc.autocorking_size
We can dynamically change the behaviour of autocorking
by change the value of autocorking_size.
Setting to 0 disables autocorking in SMC
Signed-off-by: Dust Li <dust.li@linux.alibaba.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch adds autocorking support for SMC which could improve
throughput for small message by x3+.
The main idea is borrowed from TCP autocorking with some RDMA
specific modification:
1. The first message should never cork to make sure we won't
bring extra latency
2. If we have posted any Tx WRs to the NIC that have not
completed, cork the new messages until:
a) Receive CQE for the last Tx WR
b) We have corked enough message on the connection
3. Try to push the corked data out when we receive CQE of
the last Tx WR to prevent the corked messages hang in
the send queue.
Both SMC autocorking and TCP autocorking check the TX completion
to decide whether we should cork or not. The difference is
when we got a SMC Tx WR completion, the data have been confirmed
by the RNIC while TCP TX completion just tells us the data
have been sent out by the local NIC.
Add an atomic variable tx_pushing in smc_connection to make
sure only one can send to let it cork more and save CDC slot.
SMC autocorking should not bring extra latency since the first
message will always been sent out immediately.
The qperf tcp_bw test shows more than x4 increase under small
message size with Mellanox connectX4-Lx, same result with other
throughput benchmarks like sockperf/netperf.
The qperf tcp_lat test shows SMC autocorking has not increase any
ping-pong latency.
Test command:
client: smc_run taskset -c 1 qperf smc-server -oo msg_size:1:64K:*2 \
-t 30 -vu tcp_{bw|lat}
server: smc_run taskset -c 1 qperf
=== Bandwidth ====
MsgSize(Bytes) SMC-NoCork TCP SMC-AutoCorking
1 0.578 MB/s 2.392 MB/s(313.57%) 2.647 MB/s(357.72%)
2 1.159 MB/s 4.780 MB/s(312.53%) 5.153 MB/s(344.71%)
4 2.283 MB/s 10.266 MB/s(349.77%) 10.363 MB/s(354.02%)
8 4.668 MB/s 19.040 MB/s(307.86%) 21.215 MB/s(354.45%)
16 9.147 MB/s 38.904 MB/s(325.31%) 41.740 MB/s(356.32%)
32 18.369 MB/s 79.587 MB/s(333.25%) 82.392 MB/s(348.52%)
64 36.562 MB/s 148.668 MB/s(306.61%) 161.564 MB/s(341.89%)
128 72.961 MB/s 274.913 MB/s(276.80%) 325.363 MB/s(345.94%)
256 144.705 MB/s 512.059 MB/s(253.86%) 633.743 MB/s(337.96%)
512 288.873 MB/s 884.977 MB/s(206.35%) 1250.681 MB/s(332.95%)
1024 574.180 MB/s 1337.736 MB/s(132.98%) 2246.121 MB/s(291.19%)
2048 1095.192 MB/s 1865.952 MB/s( 70.38%) 2057.767 MB/s( 87.89%)
4096 2066.157 MB/s 2380.337 MB/s( 15.21%) 2173.983 MB/s( 5.22%)
8192 3717.198 MB/s 2733.073 MB/s(-26.47%) 3491.223 MB/s( -6.08%)
16384 4742.221 MB/s 2958.693 MB/s(-37.61%) 4637.692 MB/s( -2.20%)
32768 5349.550 MB/s 3061.285 MB/s(-42.77%) 5385.796 MB/s( 0.68%)
65536 5162.919 MB/s 3731.408 MB/s(-27.73%) 5223.890 MB/s( 1.18%)
==== Latency ====
MsgSize(Bytes) SMC-NoCork TCP SMC-AutoCorking
1 10.540 us 11.938 us( 13.26%) 10.573 us( 0.31%)
2 10.996 us 11.992 us( 9.06%) 10.269 us( -6.61%)
4 10.229 us 11.687 us( 14.25%) 10.240 us( 0.11%)
8 10.203 us 11.653 us( 14.21%) 10.402 us( 1.95%)
16 10.530 us 11.313 us( 7.44%) 10.599 us( 0.66%)
32 10.241 us 11.586 us( 13.13%) 10.223 us( -0.18%)
64 10.693 us 11.652 us( 8.97%) 10.251 us( -4.13%)
128 10.597 us 11.579 us( 9.27%) 10.494 us( -0.97%)
256 10.409 us 11.957 us( 14.87%) 10.710 us( 2.89%)
512 11.088 us 12.505 us( 12.78%) 10.547 us( -4.88%)
1024 11.240 us 12.255 us( 9.03%) 10.787 us( -4.03%)
2048 11.485 us 16.970 us( 47.76%) 11.256 us( -1.99%)
4096 12.077 us 13.948 us( 15.49%) 12.230 us( 1.27%)
8192 13.683 us 16.693 us( 22.00%) 13.786 us( 0.75%)
16384 16.470 us 23.615 us( 43.38%) 16.459 us( -0.07%)
32768 22.540 us 40.966 us( 81.75%) 23.284 us( 3.30%)
65536 34.192 us 73.003 us(113.51%) 34.233 us( 0.12%)
With SMC autocorking support, we can archive better throughput
than TCP in most message sizes without any latency trade-off.
Signed-off-by: Dust Li <dust.li@linux.alibaba.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
in tunnel mode, if outer interface(ipv4) is less, it is easily to let
inner IPV6 mtu be less than 1280. If so, a Packet Too Big ICMPV6 message
is received. When send again, packets are fragmentized with 1280, they
are still rejected with ICMPV6(Packet Too Big) by xfrmi_xmit2().
According to RFC4213 Section3.2.2:
if (IPv4 path MTU - 20) is less than 1280
if packet is larger than 1280 bytes
Send ICMPv6 "packet too big" with MTU=1280
Drop packet
else
Encapsulate but do not set the Don't Fragment
flag in the IPv4 header. The resulting IPv4
packet might be fragmented by the IPv4 layer
on the encapsulator or by some router along
the IPv4 path.
endif
else
if packet is larger than (IPv4 path MTU - 20)
Send ICMPv6 "packet too big" with
MTU = (IPv4 path MTU - 20).
Drop packet.
else
Encapsulate and set the Don't Fragment flag
in the IPv4 header.
endif
endif
Packets should be fragmentized with ipv4 outer interface, so change it.
After it is fragemtized with ipv4, there will be double fragmenation.
No.48 & No.51 are ipv6 fragment packets, No.48 is double fragmentized,
then tunneled with IPv4(No.49& No.50), which obey spec. And received peer
cannot decrypt it rightly.
48 2002::10 2002::11 1296(length) IPv6 fragment (off=0 more=y ident=0xa20da5bc nxt=50)
49 0x0000 (0) 2002::10 2002::11 1304 IPv6 fragment (off=0 more=y ident=0x7448042c nxt=44)
50 0x0000 (0) 2002::10 2002::11 200 ESP (SPI=0x00035000)
51 2002::10 2002::11 180 Echo (ping) request
52 0x56dc 2002::10 2002::11 248 IPv6 fragment (off=1232 more=n ident=0xa20da5bc nxt=50)
xfrm6_noneed_fragment has fixed above issues. Finally, it acted like below:
1 0x6206 192.168.1.138 192.168.1.1 1316 Fragmented IP protocol (proto=Encap Security Payload 50, off=0, ID=6206) [Reassembled in #2]
2 0x6206 2002::10 2002::11 88 IPv6 fragment (off=0 more=y ident=0x1f440778 nxt=50)
3 0x0000 2002::10 2002::11 248 ICMPv6 Echo (ping) request
Signed-off-by: Lina Wang <lina.wang@mediatek.com>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
In case someone combines bpf socket assign and nf_queue, then we will
queue an skb who references a struct sock that did not have its
reference count incremented.
As we leave rcu protection, there is no guarantee that skb->sk is still
valid.
For refcount-less skb->sk case, try to increment the reference count
and then override the destructor.
In case of failure we have two choices: orphan the skb and 'delete'
preselect or let nf_queue() drop the packet.
Do the latter, it should not happen during normal operation.
Fixes: cf7fbe660f ("bpf: Add socket assign support")
Acked-by: Joe Stringer <joe@cilium.io>
Signed-off-by: Florian Westphal <fw@strlen.de>
Eric Dumazet says:
The sock_hold() side seems suspect, because there is no guarantee
that sk_refcnt is not already 0.
On failure, we cannot queue the packet and need to indicate an
error. The packet will be dropped by the caller.
v2: split skb prefetch hunk into separate change
Fixes: 271b72c7fa ("udp: RCU handling for Unicast packets.")
Reported-by: Eric Dumazet <eric.dumazet@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
There is no guarantee that state->sk refers to a full socket.
If refcount transitions to 0, sock_put calls sk_free which then ends up
with garbage fields.
I'd like to thank Oleksandr Natalenko and Jiri Benc for considerable
debug work and pointing out state->sk oddities.
Fixes: ca6fb06518 ("tcp: attach SYNACK messages to request sockets instead of listener")
Tested-by: Oleksandr Natalenko <oleksandr@redhat.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
When we get anti-clogging token required (added by the commit
mentioned below), or the other status codes added by the later
commit 4e56cde15f ("mac80211: Handle special status codes in
SAE commit") we currently just pretend (towards the internal
state machine of authentication) that we didn't receive anything.
This has the undesirable consequence of retransmitting the prior
frame, which is not expected, because the timer is still armed.
If we just disarm the timer at that point, it would result in
the undesirable side effect of being in this state indefinitely
if userspace crashes, or so.
So to fix this, reset the timer and set a new auth_data->waiting
in order to have no more retransmissions, but to have the data
destroyed when the timer actually fires, which will only happen
if userspace didn't continue (i.e. crashed or abandoned it.)
Fixes: a4055e74a2 ("mac80211: Don't destroy auth data in case of anti-clogging")
Reported-by: Jouni Malinen <j@w1.fi>
Link: https://lore.kernel.org/r/20220224103932.75964e1d7932.Ia487f91556f29daae734bf61f8181404642e1eec@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Initial support for the RPC_AUTH_TLS authentication flavor enables
NFSD to eventually accept an RPC_AUTH_TLS probe from clients. This
patch simply prevents NFSD from rejecting these probes completely.
In the meantime, graft this support in now so that RPC_AUTH_TLS
support keeps up with generic code and API changes in the RPC
server.
Down the road, server-side transport implementations will populate
xpo_start_tls when they can support RPC-with-TLS. For example, TCP
will eventually populate it, but RDMA won't.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Hoist svo_function back into svc_serv and remove struct
svc_serv_ops, since the struct is now devoid of fields.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
struct svc_serv_ops is about to be removed.
Neil Brown says:
> I suspect svo_module can go as well - I don't think the thread is
> ever the thing that primarily keeps a module active.
A random sample of kthread_create() callers shows sunrpc is the only
one that manages module reference count in this way.
Suggested-by: Neil Brown <neilb@suse.de>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Clean up: svc_shutdown_net() now does nothing but call
svc_close_net(). Replace all external call sites.
svc_close_net() is renamed to be the inverse of svc_xprt_create().
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Clean up. Neil observed that "any code that calls svc_shutdown_net()
knows what the shutdown function should be, and so can call it
directly."
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Reviewed-by: NeilBrown <neilb@suse.de>
Neil says:
"These functions were separated in commit 0971374e28 ("SUNRPC:
Reduce contention in svc_xprt_enqueue()") so that the XPT_BUSY check
happened before taking any spinlocks.
We have since moved or removed the spinlocks so the extra test is
fairly pointless."
I've made this a separate patch in case the XPT_BUSY change has
unexpected consequences and needs to be reverted.
Suggested-by: Neil Brown <neilb@suse.de>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
We have never been able to track down and address the underlying
cause of the performance issues with workqueue-based service
support. svo_enqueue_xprt is called multiple times per RPC, so
it adds instruction path length, but always ends up at the same
function: svc_xprt_do_enqueue(). We do not anticipate needing
this flexibility for dynamic nfsd thread management support.
As a micro-optimization, remove .svo_enqueue_xprt because
Spectre/Meltdown makes virtual function calls more costly.
This change essentially reverts commit b9e13cdfac ("nfsd/sunrpc:
turn enqueueing a svc_xprt into a svc_serv operation").
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Fix a race in the xsk socket teardown code that can lead to a NULL pointer
dereference splat. The current xsk unbind code in xsk_unbind_dev() starts by
setting xs->state to XSK_UNBOUND, sets xs->dev to NULL and then waits for any
NAPI processing to terminate using synchronize_net(). After that, the release
code starts to tear down the socket state and free allocated memory.
BUG: kernel NULL pointer dereference, address: 00000000000000c0
PGD 8000000932469067 P4D 8000000932469067 PUD 0
Oops: 0000 [#1] PREEMPT SMP PTI
CPU: 25 PID: 69132 Comm: grpcpp_sync_ser Tainted: G I 5.16.0+ #2
Hardware name: Dell Inc. PowerEdge R730/0599V5, BIOS 1.2.10 03/09/2015
RIP: 0010:__xsk_sendmsg+0x2c/0x690
[...]
RSP: 0018:ffffa2348bd13d50 EFLAGS: 00010246
RAX: 0000000000000000 RBX: 0000000000000040 RCX: ffff8d5fc632d258
RDX: 0000000000400000 RSI: ffffa2348bd13e10 RDI: ffff8d5fc5489800
RBP: ffffa2348bd13db0 R08: 0000000000000000 R09: 00007ffffffff000
R10: 0000000000000000 R11: 0000000000000000 R12: ffff8d5fc5489800
R13: ffff8d5fcb0f5140 R14: ffff8d5fcb0f5140 R15: 0000000000000000
FS: 00007f991cff9400(0000) GS:ffff8d6f1f700000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00000000000000c0 CR3: 0000000114888005 CR4: 00000000001706e0
Call Trace:
<TASK>
? aa_sk_perm+0x43/0x1b0
xsk_sendmsg+0xf0/0x110
sock_sendmsg+0x65/0x70
__sys_sendto+0x113/0x190
? debug_smp_processor_id+0x17/0x20
? fpregs_assert_state_consistent+0x23/0x50
? exit_to_user_mode_prepare+0xa5/0x1d0
__x64_sys_sendto+0x29/0x30
do_syscall_64+0x3b/0xc0
entry_SYSCALL_64_after_hwframe+0x44/0xae
There are two problems with the current code. First, setting xs->dev to NULL
before waiting for all users to stop using the socket is not correct. The
entry to the data plane functions xsk_poll(), xsk_sendmsg(), and xsk_recvmsg()
are all guarded by a test that xs->state is in the state XSK_BOUND and if not,
it returns right away. But one process might have passed this test but still
have not gotten to the point in which it uses xs->dev in the code. In this
interim, a second process executing xsk_unbind_dev() might have set xs->dev to
NULL which will lead to a crash for the first process. The solution here is
just to get rid of this NULL assignment since it is not used anymore. Before
commit 42fddcc7c6 ("xsk: use state member for socket synchronization"),
xs->dev was the gatekeeper to admit processes into the data plane functions,
but it was replaced with the state variable xs->state in the aforementioned
commit.
The second problem is that synchronize_net() does not wait for any process in
xsk_poll(), xsk_sendmsg(), or xsk_recvmsg() to complete, which means that the
state they rely on might be cleaned up prematurely. This can happen when the
notifier gets called (at driver unload for example) as it uses xsk_unbind_dev().
Solve this by extending the RCU critical region from just the ndo_xsk_wakeup
to the whole functions mentioned above, so that both the test of xs->state ==
XSK_BOUND and the last use of any member of xs is covered by the RCU critical
section. This will guarantee that when synchronize_net() completes, there will
be no processes left executing xsk_poll(), xsk_sendmsg(), or xsk_recvmsg() and
state can be cleaned up safely. Note that we need to drop the RCU lock for the
skb xmit path as it uses functions that might sleep. Due to this, we have to
retest the xs->state after we grab the mutex that protects the skb xmit code
from, among a number of things, an xsk_unbind_dev() being executed from the
notifier at the same time.
Fixes: 42fddcc7c6 ("xsk: use state member for socket synchronization")
Reported-by: Elza Mathew <elza.mathew@intel.com>
Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Björn Töpel <bjorn@kernel.org>
Link: https://lore.kernel.org/bpf/20220228094552.10134-1-magnus.karlsson@gmail.com
Use the helper function time_is_{before,after}_jiffies() to improve
code readability.
Signed-off-by: Wang Qing <wangqing@vivo.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Both rps_sock_flow_sysctl() and flow_limit_cpu_sysctl()
are using synchronize_rcu() right before freeing memory
either by vfree() or kfree()
They can switch to kvfree_rcu(ptr) and kfree_rcu(ptr) to benefit
from asynchronous mode, instead of blocking the current thread.
Note that kvfree_rcu(ptr) and kfree_rcu(ptr) eventually can
have to use synchronize_rcu() in some memory pressure cases.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch calls smc_ib_unregister_client() when tcp_register_ulp()
fails, and make sure to clean it up.
Fixes: d7cd421da9 ("net/smc: Introduce TCP ULP support")
Signed-off-by: Tony Lu <tonylu@linux.alibaba.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The current police offload action entry is missing exceed/notexceed
actions and parameters that can be configured by tc police action.
Add the missing parameters as a pre-step for offloading police actions
to hardware.
Signed-off-by: Jianbo Liu <jianbol@nvidia.com>
Signed-off-by: Roi Dayan <roid@nvidia.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
There are two reasons for addrconf_notify() to be called with NETDEV_DOWN:
either the network device is actually going down, or IPv6 was disabled
on the interface.
If either of them stays down while the other is toggled, we repeatedly
call the code for NETDEV_DOWN, including ipv6_mc_down(), while never
calling the corresponding ipv6_mc_up() in between. This will cause a
new entry in idev->mc_tomb to be allocated for each multicast group
the interface is subscribed to, which in turn leaks one struct ifmcaddr6
per nontrivial multicast group the interface is subscribed to.
The following reproducer will leak at least $n objects:
ip addr add ff2e::4242/32 dev eth0 autojoin
sysctl -w net.ipv6.conf.eth0.disable_ipv6=1
for i in $(seq 1 $n); do
ip link set up eth0; ip link set down eth0
done
Joining groups with IPV6_ADD_MEMBERSHIP (unprivileged) or setting the
sysctl net.ipv6.conf.eth0.forwarding to 1 (=> subscribing to ff02::2)
can also be used to create a nontrivial idev->mc_list, which will the
leak objects with the right up-down-sequence.
Based on both sources for NETDEV_DOWN events the interface IPv6 state
should be considered:
- not ready if the network interface is not ready OR IPv6 is disabled
for it
- ready if the network interface is ready AND IPv6 is enabled for it
The functions ipv6_mc_up() and ipv6_down() should only be run when this
state changes.
Implement this by remembering when the IPv6 state is ready, and only
run ipv6_mc_down() if it actually changed from ready to not ready.
The other direction (not ready -> ready) already works correctly, as:
- the interface notification triggered codepath for NETDEV_UP /
NETDEV_CHANGE returns early if ipv6 is disabled, and
- the disable_ipv6=0 triggered codepath skips fully initializing the
interface as long as addrconf_link_ready(dev) returns false
- calling ipv6_mc_up() repeatedly does not leak anything
Fixes: 3ce62a84d5 ("ipv6: exit early in addrconf_notify() if IPv6 is disabled")
Signed-off-by: Johannes Nixdorf <j.nixdorf@avm.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
As FDB isolation cannot be enforced between VLAN-aware bridges in lack
of hardware assistance like extra FID bits, it seems plausible that many
DSA switches cannot do it. Therefore, they need to reject configurations
with multiple VLAN-aware bridges from the two code paths that can
transition towards that state:
- joining a VLAN-aware bridge
- toggling VLAN awareness on an existing bridge
The .port_vlan_filtering method already propagates the netlink extack to
the driver, let's propagate it from .port_bridge_join too, to make sure
that the driver can use the same function for both.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
For DSA, to encourage drivers to perform FDB isolation simply means to
track which bridge does each FDB and MDB entry belong to. It then
becomes the driver responsibility to use something that makes the FDB
entry from one bridge not match the FDB lookup of ports from other
bridges.
The top-level functions where the bridge is determined are:
- dsa_port_fdb_{add,del}
- dsa_port_host_fdb_{add,del}
- dsa_port_mdb_{add,del}
- dsa_port_host_mdb_{add,del}
aka the pre-crosschip-notifier functions.
Changing the API to pass a reference to a bridge is not superfluous, and
looking at the passed bridge argument is not the same as having the
driver look at dsa_to_port(ds, port)->bridge from the ->port_fdb_add()
method.
DSA installs FDB and MDB entries on shared (CPU and DSA) ports as well,
and those do not have any dp->bridge information to retrieve, because
they are not in any bridge - they are merely the pipes that serve the
user ports that are in one or multiple bridges.
The struct dsa_bridge associated with each FDB/MDB entry is encapsulated
in a larger "struct dsa_db" database. Although only databases associated
to bridges are notified for now, this API will be the starting point for
implementing IFF_UNICAST_FLT in DSA. There, the idea is to install FDB
entries on the CPU port which belong to the corresponding user port's
port database. These are supposed to match only when the port is
standalone.
It is better to introduce the API in its expected final form than to
introduce it for bridges first, then to have to change drivers which may
have made one or more assumptions.
Drivers can use the provided bridge.num, but they can also use a
different numbering scheme that is more convenient.
DSA must perform refcounting on the CPU and DSA ports by also taking
into account the bridge number. So if two bridges request the same local
address, DSA must notify the driver twice, once for each bridge.
In fact, if the driver supports FDB isolation, DSA must perform
refcounting per bridge, but if the driver doesn't, DSA must refcount
host addresses across all bridges, otherwise it would be telling the
driver to delete an FDB entry for a bridge and the driver would delete
it for all bridges. So introduce a bool fdb_isolation in drivers which
would make all bridge databases passed to the cross-chip notifier have
the same number (0). This makes dsa_mac_addr_find() -> dsa_db_equal()
say that all bridge databases are the same database - which is
essentially the legacy behavior.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The dsa_8021q_bridge_tx_fwd_offload_vid is no longer used just for
bridge TX forwarding offload, it is the private VLAN reserved for
VLAN-unaware bridging in a way that is compatible with FDB isolation.
So just rename it dsa_tag_8021q_bridge_vid.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In the old Shared VLAN Learning mode of operation that tag_8021q
previously used for forwarding, we needed to have distinct concepts for
an RX and a TX VLAN.
An RX VLAN could be installed on all ports that were members of a given
bridge, so that autonomous forwarding could still work, while a TX VLAN
was dedicated for precise packet steering, so it just contained the CPU
port and one egress port.
Now that tag_8021q uses Independent VLAN Learning and imprecise RX/TX
all over, those lines have been blurred and we no longer have the need
to do precise TX towards a port that is in a bridge. As for standalone
ports, it is fine to use the same VLAN ID for both RX and TX.
This patch changes the tag_8021q format by shifting the VLAN range it
reserves, and halving it. Previously, our DIR bits were encoding the
VLAN direction (RX/TX) and were set to either 1 or 2. This meant that
tag_8021q reserved 2K VLANs, or 50% of the available range.
Change the DIR bits to a hardcoded value of 3 now, which makes tag_8021q
reserve only 1K VLANs, and a different range now (the last 1K). This is
done so that we leave the old format in place in case we need to return
to it.
In terms of code, the vid_is_dsa_8021q_rxvlan and vid_is_dsa_8021q_txvlan
functions go away. Any vid_is_dsa_8021q is both a TX and an RX VLAN, and
they are no longer distinct. For example, felix which did different
things for different VLAN types, now needs to handle the RX and the TX
logic for the same VLAN.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The sja1105 switch can't populate the PORT field of the tag_8021q header
when sending a frame to the CPU with a non-zero VBID.
Similar to dsa_find_designated_bridge_port_by_vid() which performs
imprecise RX for VLAN-aware bridges, let's introduce a helper in
tag_8021q for performing imprecise RX based on the VLAN that it has
allocated for a VLAN-unaware bridge.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
For VLAN-unaware bridging, tag_8021q uses something perhaps a bit too
tied with the sja1105 switch: each port uses the same pvid which is also
used for standalone operation (a unique one from which the source port
and device ID can be retrieved when packets from that port are forwarded
to the CPU). Since each port has a unique pvid when performing
autonomous forwarding, the switch must be configured for Shared VLAN
Learning (SVL) such that the VLAN ID itself is ignored when performing
FDB lookups. Without SVL, packets would always be flooded, since FDB
lookup in the source port's VLAN would never find any entry.
First of all, to make tag_8021q more palatable to switches which might
not support Shared VLAN Learning, let's just use a common VLAN for all
ports that are under the same bridge.
Secondly, using Shared VLAN Learning means that FDB isolation can never
be enforced. But if all ports under the same VLAN-unaware bridge share
the same VLAN ID, it can.
The disadvantage is that the CPU port can no longer perform precise
source port identification for these packets. But at least we have a
mechanism which has proven to be adequate for that situation: imprecise
RX (dsa_find_designated_bridge_port_by_vid), which is what we use for
termination on VLAN-aware bridges.
The VLAN ID that VLAN-unaware bridges will use with tag_8021q is the
same one as we were previously using for imprecise TX (bridge TX
forwarding offload). It is already allocated, it is just a matter of
using it.
Note that because now all ports under the same bridge share the same
VLAN, the complexity of performing a tag_8021q bridge join decreases
dramatically. We no longer have to install the RX VLAN of a newly
joining port into the port membership of the existing bridge ports.
The newly joining port just becomes a member of the VLAN corresponding
to that bridge, and the other ports are already members of it from when
they joined the bridge themselves. So forwarding works properly.
This means that we can unhook dsa_tag_8021q_bridge_{join,leave} from the
cross-chip notifier level dsa_switch_bridge_{join,leave}. We can put
these calls directly into the sja1105 driver.
With this new mode of operation, a port controlled by tag_8021q can have
two pvids whereas before it could only have one. The pvid for standalone
operation is different from the pvid used for VLAN-unaware bridging.
This is done, again, so that FDB isolation can be enforced.
Let tag_8021q manage this by deleting the standalone pvid when a port
joins a bridge, and restoring it when it leaves it.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When neighbour become invalid or destroyed, neigh_invalidate() will be
called. neigh->ops->error_report() will be called if the neighbour's
state is NUD_FAILED, and seems here is the only use of error_report().
So we can tell that the reason of skb drops in arp_error_report() is
SKB_DROP_REASON_NEIGH_FAILED.
Replace kfree_skb() used in arp_error_report() with kfree_skb_reason().
Reviewed-by: Mengen Sun <mengensun@tencent.com>
Reviewed-by: Hao Peng <flyingpeng@tencent.com>
Signed-off-by: Menglong Dong <imagedong@tencent.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Replace kfree_skb() used in __neigh_event_send() with
kfree_skb_reason(). Following drop reasons are added:
SKB_DROP_REASON_NEIGH_FAILED
SKB_DROP_REASON_NEIGH_QUEUEFULL
SKB_DROP_REASON_NEIGH_DEAD
The first two reasons above should be the hot path that skb drops
in neighbour subsystem.
Reviewed-by: Mengen Sun <mengensun@tencent.com>
Reviewed-by: Hao Peng <flyingpeng@tencent.com>
Signed-off-by: Menglong Dong <imagedong@tencent.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Replace kfree_skb() which is used in the packet egress path of IP layer
with kfree_skb_reason(). Functions that are involved include:
__ip_queue_xmit()
ip_finish_output()
ip_mc_finish_output()
ip6_output()
ip6_finish_output()
ip6_finish_output2()
Following new drop reasons are introduced:
SKB_DROP_REASON_IP_OUTNOROUTES
SKB_DROP_REASON_BPF_CGROUP_EGRESS
SKB_DROP_REASON_IPV6DISABLED
SKB_DROP_REASON_NEIGH_CREATEFAIL
Reviewed-by: Mengen Sun <mengensun@tencent.com>
Reviewed-by: Hao Peng <flyingpeng@tencent.com>
Signed-off-by: Menglong Dong <imagedong@tencent.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Previously if an unregister notify handler ran twice (waiting for
netdev to be released) it would print a warning in mctp_unregister()
every subsequent time the unregister notify occured.
Instead we only need to worry about the case where a mctp_ptr is
set on an unknown device type.
Signed-off-by: Matt Johnston <matt@codeconstruct.com.au>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
The sections which should not re-enter the filesystem are already
protected with memalloc_nofs_save/restore calls, so it is better to use
GFP_KERNEL in these calls to allow better performance for synchronous
RPC calls.
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Steffen Klassert says:
====================
1) Fix PMTU for IPv6 if the reported MTU minus the ESP overhead is
smaller than 1280. From Jiri Bohac.
2) Fix xfrm interface ID and inter address family tunneling when
migrating xfrm states. From Yan Yan.
3) Add missing xfrm intrerface ID initialization on xfrmi_changelink.
From Antony Antony.
4) Enforce validity of xfrm offload input flags so that userspace can't
send undefined flags to the offload driver.
From Leon Romanovsky.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
