The 'drop_reason' that passed to kfree_skb_reason() in tcp_v4_rcv()
and tcp_v6_rcv() can be SKB_NOT_DROPPED_YET(0), as it is used as the
return value of tcp_inbound_md5_hash().
And it can panic the kernel with NULL pointer in
net_dm_packet_report_size() if the reason is 0, as drop_reasons[0]
is NULL.
Fixes: 1330b6ef33 ("skb: make drop reason booleanable")
Reviewed-by: Jiang Biao <benbjiang@tencent.com>
Reviewed-by: Hao Peng <flyingpeng@tencent.com>
Signed-off-by: Menglong Dong <imagedong@tencent.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This is no longer a macro, but an inlined function.
INET_MATCH() -> inet_match()
Signed-off-by: Eric Dumazet <edumazet@google.com>
Suggested-by: Olivier Hartkopp <socketcan@hartkopp.net>
Suggested-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
INET6_MATCH() runs without holding a lock on the socket.
We probably need to annotate most reads.
This patch makes INET6_MATCH() an inline function
to ease our changes.
v2: inline function only defined if IS_ENABLED(CONFIG_IPV6)
Change the name to inet6_match(), this is no longer a macro.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
inet_csk_bind_conflict() can access sk->sk_bound_dev_if for
unlocked sockets.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
hystart_ack_delay() had the assumption that a TSO packet
would not be bigger than GSO_MAX_SIZE.
This will no longer be true.
We should use sk->sk_gso_max_size instead.
This reduces chances of spurious Hystart ACK train detections.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Alexander Duyck <alexanderduyck@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The code for gso_max_size was added originally to allow for debugging and
workaround of buggy devices that couldn't support TSO with blocks 64K in
size. The original reason for limiting it to 64K was because that was the
existing limits of IPv4 and non-jumbogram IPv6 length fields.
With the addition of Big TCP we can remove this limit and allow the value
to potentially go up to UINT_MAX and instead be limited by the tso_max_size
value.
So in order to support this we need to go through and clean up the
remaining users of the gso_max_size value so that the values will cap at
64K for non-TCPv6 flows. In addition we can clean up the GSO_MAX_SIZE value
so that 64K becomes GSO_LEGACY_MAX_SIZE and UINT_MAX will now be the upper
limit for GSO_MAX_SIZE.
v6: (edumazet) fixed a compile error if CONFIG_IPV6=n,
in a new sk_trim_gso_size() helper.
netif_set_tso_max_size() caps the requested TSO size
with GSO_MAX_SIZE.
Signed-off-by: Alexander Duyck <alexanderduyck@fb.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Pablo Neira Ayuso says:
====================
Netfilter updates for net-next
This is v2 including deadlock fix in conntrack ecache rework
reported by Jakub Kicinski.
The following patchset contains Netfilter updates for net-next,
mostly updates to conntrack from Florian Westphal.
1) Add a dedicated list for conntrack event redelivery.
2) Include event redelivery list in conntrack dumps of dying type.
3) Remove per-cpu dying list for event redelivery, not used anymore.
4) Add netns .pre_exit to cttimeout to zap timeout objects before
synchronize_rcu() call.
5) Remove nf_ct_unconfirmed_destroy.
6) Add generation id for conntrack extensions for conntrack
timeout and helpers.
7) Detach timeout policy from conntrack on cttimeout module removal.
8) Remove __nf_ct_unconfirmed_destroy.
9) Remove unconfirmed list.
10) Remove unconditional local_bh_disable in init_conntrack().
11) Consolidate conntrack iterator nf_ct_iterate_cleanup().
12) Detect if ctnetlink listeners exist to short-circuit event
path early.
13) Un-inline nf_ct_ecache_ext_add().
14) Add nf_conntrack_events autodetect ctnetlink listener mode
and make it default.
15) Add nf_ct_ecache_exist() to check for event cache extension.
16) Extend flowtable reverse route lookup to include source, iif,
tos and mark, from Sven Auhagen.
17) Do not verify zero checksum UDP packets in nf_reject,
from Kevin Mitchell.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Steffen Klassert says:
====================
pull request (net-next): ipsec-next 2022-05-13
1) Cleanups for the code behind the XFRM offload API. This is a
preparation for the extension of the API for policy offload.
From Leon Romanovsky.
* 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/klassert/ipsec-next:
xfrm: drop not needed flags variable in XFRM offload struct
net/mlx5e: Use XFRM state direction instead of flags
netdevsim: rely on XFRM state direction instead of flags
ixgbe: propagate XFRM offload state direction instead of flags
xfrm: store and rely on direction to construct offload flags
xfrm: rename xfrm_state_offload struct to allow reuse
xfrm: delete not used number of external headers
xfrm: free not used XFRM_ESP_NO_TRAILER flag
====================
Link: https://lore.kernel.org/r/20220513151218.4010119-1-steffen.klassert@secunet.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
The checksum is optional for UDP packets. However nf_reject would
previously require a valid checksum to elicit a response such as
ICMP_DEST_UNREACH.
Add some logic to nf_reject_verify_csum to determine if a UDP packet has
a zero checksum and should therefore not be verified.
Signed-off-by: Kevin Mitchell <kevmitch@arista.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
INET_MATCH() runs without holding a lock on the socket.
We probably need to annotate most reads.
This patch makes INET_MATCH() an inline function
to ease our changes.
v2:
We remove the 32bit version of it, as modern compilers
should generate the same code really, no need to
try to be smarter.
Also make 'struct net *net' the first argument.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The listen sk is currently stored in two hash tables,
listening_hash (hashed by port) and lhash2 (hashed by port and address).
After commit 0ee58dad5b ("net: tcp6: prefer listeners bound to an address")
and commit d9fbc7f643 ("net: tcp: prefer listeners bound to an address"),
the TCP-SYN lookup fast path does not use listening_hash.
The commit 05c0b35709 ("tcp: seq_file: Replace listening_hash with lhash2")
also moved the seq_file (/proc/net/tcp) iteration usage from
listening_hash to lhash2.
There are still a few listening_hash usages left.
One of them is inet_reuseport_add_sock() which uses the listening_hash
to search a listen sk during the listen() system call. This turns
out to be very slow on use cases that listen on many different
VIPs at a popular port (e.g. 443). [ On top of the slowness in
adding to the tail in the IPv6 case ]. The latter patch has a
selftest to demonstrate this case.
This patch takes this chance to move all remaining listening_hash
usages to lhash2 and then retire listening_hash.
Since most changes need to be done together, it is hard to cut
the listening_hash to lhash2 switch into small patches. The
changes in this patch is highlighted here for the review
purpose.
1. Because of the listening_hash removal, lhash2 can use the
sk->sk_nulls_node instead of the icsk->icsk_listen_portaddr_node.
This will also keep the sk_unhashed() check to work as is
after stop adding sk to listening_hash.
The union is removed from inet_listen_hashbucket because
only nulls_head is needed.
2. icsk->icsk_listen_portaddr_node and its helpers are removed.
3. The current lhash2 users needs to iterate with sk_nulls_node
instead of icsk_listen_portaddr_node.
One case is in the inet[6]_lhash2_lookup().
Another case is the seq_file iterator in tcp_ipv4.c.
One thing to note is sk_nulls_next() is needed
because the old inet_lhash2_for_each_icsk_continue()
does a "next" first before iterating.
4. Move the remaining listening_hash usage to lhash2
inet_reuseport_add_sock() which this series is
trying to improve.
inet_diag.c and mptcp_diag.c are the final two
remaining use cases and is moved to lhash2 now also.
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
This patch folds lhash2 related functions into __inet_hash and
inet_unhash. This will make the removal of the listening_hash
in a latter patch easier to review.
First, this patch folds inet_hash2 into __inet_hash.
For unhash, the current call sequence is like
inet_unhash() => __inet_unhash() => inet_unhash2().
The specific testing cases in __inet_unhash() are mostly related
to TCP_LISTEN sk and its caller inet_unhash() already has
the TCP_LISTEN test, so this patch folds both __inet_unhash() and
inet_unhash2() into inet_unhash().
Note that all listening_hash users also have lhash2 initialized,
so the !h->lhash2 check is no longer needed.
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
After commit 0ee58dad5b ("net: tcp6: prefer listeners bound to an address")
and commit d9fbc7f643 ("net: tcp: prefer listeners bound to an address"),
the count is no longer used. This patch removes it.
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
After removal of Innova IPsec support from mlx5 driver, the last user
of this XFRM_ESP_NO_TRAILER was gone too. This means that we can safely
remove it as no other hardware is capable (or need) to remove ESP trailer.
Reviewed-by: Raed Salem <raeds@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
The MPTCP RFC requires that the MPTCP-level receive window's
right edge never moves backward. Currently the MPTCP code
enforces such constraint while tracking the right edge, but it
does not reflects it on the wire, as MPTCP lacks a suitable hook
to update accordingly the TCP header.
This change modifies the existing mptcp_write_options() hook,
providing the current packet's TCP header to the MPTCP protocol,
so that the next patch could implement the above mentioned
constraint.
No functional changes intended.
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
When ping_group_range is updated, 'ping' uses the DGRAM ICMP socket,
instead of an IP raw socket. In this case, 'ping' is unable to bind its
socket to a local address owned by a vrflite.
Before the patch:
$ sysctl -w net.ipv4.ping_group_range='0 2147483647'
$ ip link add blue type vrf table 10
$ ip link add foo type dummy
$ ip link set foo master blue
$ ip link set foo up
$ ip addr add 192.168.1.1/24 dev foo
$ ip addr add 2001::1/64 dev foo
$ ip vrf exec blue ping -c1 -I 192.168.1.1 192.168.1.2
ping: bind: Cannot assign requested address
$ ip vrf exec blue ping6 -c1 -I 2001::1 2001::2
ping6: bind icmp socket: Cannot assign requested address
CC: stable@vger.kernel.org
Fixes: 1b69c6d0ae ("net: Introduce L3 Master device abstraction")
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
In commit 190cc82489 ("tcp: change source port randomizarion at
connect() time"), the table_perturb[] array was introduced and an
index was taken from the port_offset via hash_32(). But it turns
out that hash_32() performs a multiplication while the input here
comes from the output of SipHash in secure_seq, that is well
distributed enough to avoid the need for yet another hash.
Suggested-by: Amit Klein <aksecurity@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Willy Tarreau <w@1wt.eu>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Moshe Kol, Amit Klein, and Yossi Gilad reported being able to accurately
identify a client by forcing it to emit only 40 times more connections
than there are entries in the table_perturb[] table. The previous two
improvements consisting in resalting the secret every 10s and adding
randomness to each port selection only slightly improved the situation,
and the current value of 2^8 was too small as it's not very difficult
to make a client emit 10k connections in less than 10 seconds.
Thus we're increasing the perturb table from 2^8 to 2^16 so that the
same precision now requires 2.6M connections, which is more difficult in
this time frame and harder to hide as a background activity. The impact
is that the table now uses 256 kB instead of 1 kB, which could mostly
affect devices making frequent outgoing connections. However such
components usually target a small set of destinations (load balancers,
database clients, perf assessment tools), and in practice only a few
entries will be visited, like before.
A live test at 1 million connections per second showed no performance
difference from the previous value.
Reported-by: Moshe Kol <moshe.kol@mail.huji.ac.il>
Reported-by: Yossi Gilad <yossi.gilad@mail.huji.ac.il>
Reported-by: Amit Klein <aksecurity@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Willy Tarreau <w@1wt.eu>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
We'll need to further increase the size of this table and it's likely
that at some point its size will not be suitable anymore for a static
table. Let's allocate it on boot from inet_hashinfo2_init(), which is
called from tcp_init().
Cc: Moshe Kol <moshe.kol@mail.huji.ac.il>
Cc: Yossi Gilad <yossi.gilad@mail.huji.ac.il>
Cc: Amit Klein <aksecurity@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Willy Tarreau <w@1wt.eu>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Here we're randomly adding between 0 and 7 random increments to the
selected source port in order to add some noise in the source port
selection that will make the next port less predictable.
With the default port range of 32768-60999 this means a worst case
reuse scenario of 14116/8=1764 connections between two consecutive
uses of the same port, with an average of 14116/4.5=3137. This code
was stressed at more than 800000 connections per second to a fixed
target with all connections closed by the client using RSTs (worst
condition) and only 2 connections failed among 13 billion, despite
the hash being reseeded every 10 seconds, indicating a perfectly
safe situation.
Cc: Moshe Kol <moshe.kol@mail.huji.ac.il>
Cc: Yossi Gilad <yossi.gilad@mail.huji.ac.il>
Cc: Amit Klein <aksecurity@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Willy Tarreau <w@1wt.eu>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Amit Klein suggests that we use different parts of port_offset for the
table's index and the port offset so that there is no direct relation
between them.
Cc: Jason A. Donenfeld <Jason@zx2c4.com>
Cc: Moshe Kol <moshe.kol@mail.huji.ac.il>
Cc: Yossi Gilad <yossi.gilad@mail.huji.ac.il>
Cc: Amit Klein <aksecurity@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Willy Tarreau <w@1wt.eu>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
SipHash replaced MD5 in secure_ipv{4,6}_port_ephemeral() via commit
7cd23e5300 ("secure_seq: use SipHash in place of MD5"), but the output
remained truncated to 32-bit only. In order to exploit more bits from the
hash, let's make the functions return the full 64-bit of siphash_3u32().
We also make sure the port offset calculation in __inet_hash_connect()
remains done on 32-bit to avoid the need for div_u64_rem() and an extra
cost on 32-bit systems.
Cc: Jason A. Donenfeld <Jason@zx2c4.com>
Cc: Moshe Kol <moshe.kol@mail.huji.ac.il>
Cc: Yossi Gilad <yossi.gilad@mail.huji.ac.il>
Cc: Amit Klein <aksecurity@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Willy Tarreau <w@1wt.eu>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Creating a new netdevice allocates at least ~50Kb of memory for various
kernel objects, but only ~5Kb of them are accounted to memcg. As a result,
creating an unlimited number of netdevice inside a memcg-limited container
does not fall within memcg restrictions, consumes a significant part
of the host's memory, can cause global OOM and lead to random kills of
host processes.
The main consumers of non-accounted memory are:
~10Kb 80+ kernfs nodes
~6Kb ipv6_add_dev() allocations
6Kb __register_sysctl_table() allocations
4Kb neigh_sysctl_register() allocations
4Kb __devinet_sysctl_register() allocations
4Kb __addrconf_sysctl_register() allocations
Accounting of these objects allows to increase the share of memcg-related
memory up to 60-70% (~38Kb accounted vs ~54Kb total for dummy netdevice
on typical VM with default Fedora 35 kernel) and this should be enough
to somehow protect the host from misuse inside container.
Other related objects are quite small and may not be taken into account
to minimize the expected performance degradation.
It should be separately mentonied ~300 bytes of percpu allocation
of struct ipstats_mib in snmp6_alloc_dev(), on huge multi-cpu nodes
it can become the main consumer of memory.
This patch does not enables kernfs accounting as it affects
other parts of the kernel and should be discussed separately.
However, even without kernfs, this patch significantly improves the
current situation and allows to take into account more than half
of all netdevice allocations.
Signed-off-by: Vasily Averin <vvs@openvz.org>
Acked-by: Luis Chamberlain <mcgrof@kernel.org>
Link: https://lore.kernel.org/r/354a0a5f-9ec3-a25c-3215-304eab2157bc@openvz.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Recently we made o_seqno atomic_t. Stop special-casing TUNNEL_SEQ, and
always mark GRE[TAP] devices as NETIF_F_LLTX, since we no longer need
the TX lock (&txq->_xmit_lock).
Signed-off-by: Peilin Ye <peilin.ye@bytedance.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
This patch doesn't change any functionality.
Signed-off-by: Pengcheng Yang <yangpc@wangsu.com>
Cc: Neal Cardwell <ncardwell@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Tested-by: Neal Cardwell <ncardwell@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In commit f84af32cbc ("net: ip_queue_rcv_skb() helper")
I dropped the skb dst in tcp_data_queue().
This only dealt with so-called TCP input slow path.
When fast path is taken, tcp_rcv_established() calls
tcp_queue_rcv() while skb still has a dst.
This was mostly fine, because most dsts at this point
are not refcounted (thanks to early demux)
However, TCP packets sent over loopback have refcounted dst.
Then commit 68822bdf76 ("net: generalize skb freeing
deferral to per-cpu lists") came and had the effect
of delaying skb freeing for an arbitrary time.
If during this time the involved netns is dismantled, cleanup_net()
frees the struct net with embedded net->ipv6.ip6_dst_ops.
Then when eventually dst_destroy_rcu() is called,
if (dst->ops->destroy) ... triggers an use-after-free.
It is not clear if ip6_route_net_exit() lacks a rcu_barrier()
as syzbot reported similar issues before the blamed commit.
( https://groups.google.com/g/syzkaller-bugs/c/CofzW4eeA9A/m/009WjumTAAAJ )
Fixes: 68822bdf76 ("net: generalize skb freeing deferral to per-cpu lists")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This is currently done for CMSG_INQ, add an ability to do so via struct
msghdr as well and have CMSG_INQ use that too. If the caller sets
msghdr->msg_get_inq, then we'll pass back the hint in msghdr->msg_inq.
Rearrange struct msghdr a bit so we can add this member while shrinking
it at the same time. On a 64-bit build, it was 96 bytes before this
change and 88 bytes afterwards.
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Link: https://lore.kernel.org/r/650c22ca-cffc-0255-9a05-2413a1e20826@kernel.dk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Adding a new socket option, SO_RCVMARK, to indicate that SO_MARK
should be included in the ancillary data returned by recvmsg().
Renamed the sock_recv_ts_and_drops() function to sock_recv_cmsgs().
Signed-off-by: Erin MacNeil <lnx.erin@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Acked-by: Marc Kleine-Budde <mkl@pengutronix.de>
Link: https://lore.kernel.org/r/20220427200259.2564-1-lnx.erin@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Logic added in commit f35f821935 ("tcp: defer skb freeing after socket
lock is released") helped bulk TCP flows to move the cost of skbs
frees outside of critical section where socket lock was held.
But for RPC traffic, or hosts with RFS enabled, the solution is far from
being ideal.
For RPC traffic, recvmsg() has to return to user space right after
skb payload has been consumed, meaning that BH handler has no chance
to pick the skb before recvmsg() thread. This issue is more visible
with BIG TCP, as more RPC fit one skb.
For RFS, even if BH handler picks the skbs, they are still picked
from the cpu on which user thread is running.
Ideally, it is better to free the skbs (and associated page frags)
on the cpu that originally allocated them.
This patch removes the per socket anchor (sk->defer_list) and
instead uses a per-cpu list, which will hold more skbs per round.
This new per-cpu list is drained at the end of net_action_rx(),
after incoming packets have been processed, to lower latencies.
In normal conditions, skbs are added to the per-cpu list with
no further action. In the (unlikely) cases where the cpu does not
run net_action_rx() handler fast enough, we use an IPI to raise
NET_RX_SOFTIRQ on the remote cpu.
Also, we do not bother draining the per-cpu list from dev_cpu_dead()
This is because skbs in this list have no requirement on how fast
they should be freed.
Note that we can add in the future a small per-cpu cache
if we see any contention on sd->defer_lock.
Tested on a pair of hosts with 100Gbit NIC, RFS enabled,
and /proc/sys/net/ipv4/tcp_rmem[2] tuned to 16MB to work around
page recycling strategy used by NIC driver (its page pool capacity
being too small compared to number of skbs/pages held in sockets
receive queues)
Note that this tuning was only done to demonstrate worse
conditions for skb freeing for this particular test.
These conditions can happen in more general production workload.
10 runs of one TCP_STREAM flow
Before:
Average throughput: 49685 Mbit.
Kernel profiles on cpu running user thread recvmsg() show high cost for
skb freeing related functions (*)
57.81% [kernel] [k] copy_user_enhanced_fast_string
(*) 12.87% [kernel] [k] skb_release_data
(*) 4.25% [kernel] [k] __free_one_page
(*) 3.57% [kernel] [k] __list_del_entry_valid
1.85% [kernel] [k] __netif_receive_skb_core
1.60% [kernel] [k] __skb_datagram_iter
(*) 1.59% [kernel] [k] free_unref_page_commit
(*) 1.16% [kernel] [k] __slab_free
1.16% [kernel] [k] _copy_to_iter
(*) 1.01% [kernel] [k] kfree
(*) 0.88% [kernel] [k] free_unref_page
0.57% [kernel] [k] ip6_rcv_core
0.55% [kernel] [k] ip6t_do_table
0.54% [kernel] [k] flush_smp_call_function_queue
(*) 0.54% [kernel] [k] free_pcppages_bulk
0.51% [kernel] [k] llist_reverse_order
0.38% [kernel] [k] process_backlog
(*) 0.38% [kernel] [k] free_pcp_prepare
0.37% [kernel] [k] tcp_recvmsg_locked
(*) 0.37% [kernel] [k] __list_add_valid
0.34% [kernel] [k] sock_rfree
0.34% [kernel] [k] _raw_spin_lock_irq
(*) 0.33% [kernel] [k] __page_cache_release
0.33% [kernel] [k] tcp_v6_rcv
(*) 0.33% [kernel] [k] __put_page
(*) 0.29% [kernel] [k] __mod_zone_page_state
0.27% [kernel] [k] _raw_spin_lock
After patch:
Average throughput: 73076 Mbit.
Kernel profiles on cpu running user thread recvmsg() looks better:
81.35% [kernel] [k] copy_user_enhanced_fast_string
1.95% [kernel] [k] _copy_to_iter
1.95% [kernel] [k] __skb_datagram_iter
1.27% [kernel] [k] __netif_receive_skb_core
1.03% [kernel] [k] ip6t_do_table
0.60% [kernel] [k] sock_rfree
0.50% [kernel] [k] tcp_v6_rcv
0.47% [kernel] [k] ip6_rcv_core
0.45% [kernel] [k] read_tsc
0.44% [kernel] [k] _raw_spin_lock_irqsave
0.37% [kernel] [k] _raw_spin_lock
0.37% [kernel] [k] native_irq_return_iret
0.33% [kernel] [k] __inet6_lookup_established
0.31% [kernel] [k] ip6_protocol_deliver_rcu
0.29% [kernel] [k] tcp_rcv_established
0.29% [kernel] [k] llist_reverse_order
v2: kdoc issue (kernel bots)
do not defer if (alloc_cpu == smp_processor_id()) (Paolo)
replace the sk_buff_head with a single-linked list (Jakub)
add a READ_ONCE()/WRITE_ONCE() for the lockless read of sd->defer_list
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Link: https://lore.kernel.org/r/20220422201237.416238-1-eric.dumazet@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
I had this bug sitting for too long in my pile, it is time to fix it.
Thanks to Doug Porter for reminding me of it!
We had various attempts in the past, including commit
0cbe6a8f08 ("tcp: remove SOCK_QUEUE_SHRUNK"),
but the issue is that TCP stack currently only generates
EPOLLOUT from input path, when tp->snd_una has advanced
and skb(s) cleaned from rtx queue.
If a flow has a big RTT, and/or receives SACKs, it is possible
that the notsent part (tp->write_seq - tp->snd_nxt) reaches 0
and no more data can be sent until tp->snd_una finally advances.
What is needed is to also check if POLLOUT needs to be generated
whenever tp->snd_nxt is advanced, from output path.
This bug triggers more often after an idle period, as
we do not receive ACK for at least one RTT. tcp_notsent_lowat
could be a fraction of what CWND and pacing rate would allow to
send during this RTT.
In a followup patch, I will remove the bogus call
to tcp_chrono_stop(sk, TCP_CHRONO_SNDBUF_LIMITED)
from tcp_check_space(). Fact that we have decided to generate
an EPOLLOUT does not mean the application has immediately
refilled the transmit queue. This optimistic call
might have been the reason the bug seemed not too serious.
Tested:
200 ms rtt, 1% packet loss, 32 MB tcp_rmem[2] and tcp_wmem[2]
$ echo 500000 >/proc/sys/net/ipv4/tcp_notsent_lowat
$ cat bench_rr.sh
SUM=0
for i in {1..10}
do
V=`netperf -H remote_host -l30 -t TCP_RR -- -r 10000000,10000 -o LOCAL_BYTES_SENT | egrep -v "MIGRATED|Bytes"`
echo $V
SUM=$(($SUM + $V))
done
echo SUM=$SUM
Before patch:
$ bench_rr.sh
130000000
80000000
140000000
140000000
140000000
140000000
130000000
40000000
90000000
110000000
SUM=1140000000
After patch:
$ bench_rr.sh
430000000
590000000
530000000
450000000
450000000
350000000
450000000
490000000
480000000
460000000
SUM=4680000000 # This is 410 % of the value before patch.
Fixes: c9bee3b7fd ("tcp: TCP_NOTSENT_LOWAT socket option")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Doug Porter <dsp@fb.com>
Cc: Soheil Hassas Yeganeh <soheil@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
As pointed out by Jakub Kicinski, currently using TUNNEL_SEQ in
collect_md mode is racy for [IP6]GRE[TAP] devices. Consider the
following sequence of events:
1. An [IP6]GRE[TAP] device is created in collect_md mode using "ip link
add ... external". "ip" ignores "[o]seq" if "external" is specified,
so TUNNEL_SEQ is off, and the device is marked as NETIF_F_LLTX (i.e.
it uses lockless TX);
2. Someone sets TUNNEL_SEQ on outgoing skb's, using e.g.
bpf_skb_set_tunnel_key() in an eBPF program attached to this device;
3. gre_fb_xmit() or __gre6_xmit() processes these skb's:
gre_build_header(skb, tun_hlen,
flags, protocol,
tunnel_id_to_key32(tun_info->key.tun_id),
(flags & TUNNEL_SEQ) ? htonl(tunnel->o_seqno++)
: 0); ^^^^^^^^^^^^^^^^^
Since we are not using the TX lock (&txq->_xmit_lock), multiple CPUs may
try to do this tunnel->o_seqno++ in parallel, which is racy. Fix it by
making o_seqno atomic_t.
As mentioned by Eric Dumazet in commit b790e01aee ("ip_gre: lockless
xmit"), making o_seqno atomic_t increases "chance for packets being out
of order at receiver" when NETIF_F_LLTX is on.
Maybe a better fix would be:
1. Do not ignore "oseq" in external mode. Users MUST specify "oseq" if
they want the kernel to allow sequencing of outgoing packets;
2. Reject all outgoing TUNNEL_SEQ packets if the device was not created
with "oseq".
Unfortunately, that would break userspace.
We could now make [IP6]GRE[TAP] devices always NETIF_F_LLTX, but let us
do it in separate patches to keep this fix minimal.
Suggested-by: Jakub Kicinski <kuba@kernel.org>
Fixes: 77a5196a80 ("gre: add sequence number for collect md mode.")
Signed-off-by: Peilin Ye <peilin.ye@bytedance.com>
Acked-by: William Tu <u9012063@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
For GRE and GRETAP devices, currently o_seqno starts from 1 in native
mode. According to RFC 2890 2.2., "The first datagram is sent with a
sequence number of 0." Fix it.
It is worth mentioning that o_seqno already starts from 0 in collect_md
mode, see gre_fb_xmit(), where tunnel->o_seqno is passed to
gre_build_header() before getting incremented.
Fixes: 1da177e4c3 ("Linux-2.6.12-rc2")
Signed-off-by: Peilin Ye <peilin.ye@bytedance.com>
Acked-by: William Tu <u9012063@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Pablo Neira Ayuso says:
====================
Netfilter fixes for net
The following patchset contains Netfilter fixes for net:
1) Fix incorrect printing of memory size of IPVS connection hash table,
from Pengcheng Yang.
2) Fix spurious EEXIST errors in nft_set_rbtree.
3) Remove leftover empty flowtable file, from Rongguang Wei.
4) Fix ip6_route_me_harder() with vrf driver, from Martin Willi.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
CONFIG_NF_FLOW_TABLE_IPV4 is already removed and the real user is also
removed(nf_flow_table_ipv4.c is empty).
Fixes: c42ba4290b ("netfilter: flowtable: remove ipv4/ipv6 modules")
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
If an ACK (s)acks multiple skbs, we favor the information
from the most recently sent skb by choosing the skb with
the highest prior_delivered count. But in the interval
between receiving ACKs, we send multiple skbs with the same
prior_delivered, because the tp->delivered only changes
when we receive an ACK.
We used RACK's solution, copying tcp_rack_sent_after() as
tcp_skb_sent_after() helper to determine "which packet was
sent last?". Later, we will use tcp_skb_sent_after() instead
in RACK.
Fixes: b9f64820fb ("tcp: track data delivery rate for a TCP connection")
Signed-off-by: Pengcheng Yang <yangpc@wangsu.com>
Cc: Paolo Abeni <pabeni@redhat.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Tested-by: Neal Cardwell <ncardwell@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/1650422081-22153-1-git-send-email-yangpc@wangsu.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
In tcp_create_openreq_child we adjust tcp_header_len for md5 using the
remote address in newsk. But that address is still 0 in newsk at this
point, and it is only set later by the callers (tcp_v[46]_syn_recv_sock).
Use the address from the request socket instead.
Fixes: cfb6eeb4c8 ("[TCP]: MD5 Signature Option (RFC2385) support.")
Signed-off-by: Francesco Ruggeri <fruggeri@arista.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20220421005026.686A45EC01F2@us226.sjc.aristanetworks.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
All the *_redirect() and *_update_pmtu() functions initialise their
struct flowi4 variable with either __build_flow_key() or
build_sk_flow_key(). When sk is provided, these functions use
RT_CONN_FLAGS() to set ->flowi4_tos and always use RT_SCOPE_UNIVERSE
for ->flowi4_scope. Then they rely on ip_rt_fix_tos() to adjust the
scope based on the RTO_ONLINK bit and to mask the tos with
IPTOS_RT_MASK.
This patch modifies __build_flow_key() and build_sk_flow_key() to
properly initialise ->flowi4_tos and ->flowi4_scope, so that the
ICMP redirects and PMTU handlers don't need an extra call to
ip_rt_fix_tos() before doing a fib lookup. That is, we:
* Drop RT_CONN_FLAGS(): use ip_sock_rt_tos() and ip_sock_rt_scope()
instead, so that we don't have to rely on ip_rt_fix_tos() to adjust
the scope anymore.
* Apply IPTOS_RT_MASK to the tos, so that we don't need
ip_rt_fix_tos() to do it for us.
* Drop the ip_rt_fix_tos() calls that now become useless.
The only remaining ip_rt_fix_tos() caller is ip_route_output_key_hash()
which needs it as long as external callers still use the RTO_ONLINK
flag.
Note:
This patch also drops some useless RT_TOS() calls as IPTOS_RT_MASK is
a stronger mask.
Signed-off-by: Guillaume Nault <gnault@redhat.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Now that ip_rt_fix_tos() doesn't reset ->flowi4_scope unconditionally,
we don't have to rely on the RTO_ONLINK bit to properly set the scope
of a flowi4 structure. We can just set ->flowi4_scope explicitly and
avoid using RTO_ONLINK in ->flowi4_tos.
This patch converts callers of ip_route_connect(). Instead of setting
the tos parameter with RT_CONN_FLAGS(sk), as all callers do, we can:
1- Drop the tos parameter from ip_route_connect(): its value was
entirely based on sk, which is also passed as parameter.
2- Set ->flowi4_scope depending on the SOCK_LOCALROUTE socket option
instead of always initialising it with RT_SCOPE_UNIVERSE (let's
define ip_sock_rt_scope() for this purpose).
3- Avoid overloading ->flowi4_tos with RTO_ONLINK: since the scope is
now properly initialised, we don't need to tell ip_rt_fix_tos() to
adjust ->flowi4_scope for us. So let's define ip_sock_rt_tos(),
which is the same as RT_CONN_FLAGS() but without the RTO_ONLINK
bit overload.
Note:
In the original ip_route_connect() code, __ip_route_output_key()
might clear the RTO_ONLINK bit of fl4->flowi4_tos (because of
ip_rt_fix_tos()). Therefore flowi4_update_output() had to reuse the
original tos variable. Now that we don't set RTO_ONLINK any more,
this is not a problem and we can use fl4->flowi4_tos in
flowi4_update_output().
Signed-off-by: Guillaume Nault <gnault@redhat.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
