This patch allows bpf tcp iter to call bpf_(get|set)sockopt.
To allow a specific bpf iter (tcp here) to call a set of helpers,
get_func_proto function pointer is added to bpf_iter_reg.
The bpf iter is a tracing prog which currently requires
CAP_PERFMON or CAP_SYS_ADMIN, so this patch does not
impose other capability checks for bpf_(get|set)sockopt.
Signed-off-by: NMartin KaFai Lau <kafai@fb.com>
Signed-off-by: NAndrii Nakryiko <andrii@kernel.org>
Reviewed-by: NEric Dumazet <edumazet@google.com>
Acked-by: NKuniyuki Iwashima <kuniyu@amazon.co.jp>
Acked-by: NYonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/bpf/20210701200619.1036715-1-kafai@fb.com

This patch does batching and lock_sock for the bpf tcp iter.
It does not affect the proc fs iteration.

With bpf-tcp-cc, new algo rollout happens more often.  Instead of
restarting the application to pick up the new tcp-cc, the next patch
will allow bpf iter to do setsockopt(TCP_CONGESTION).  This requires
locking the sock.

Also, unlike the proc iteration (cat /proc/net/tcp[6]), the bpf iter
can inspect all fields of a tcp_sock.  It will be useful to have a
consistent view on some of the fields (e.g. the ones reported in
tcp_get_info() that also acquires the sock lock).

Double lock: locking the bucket first and then locking the sock could
lead to deadlock.  This patch takes a batching approach similar to
inet_diag.  While holding the bucket lock, it batch a number of sockets
into an array first and then unlock the bucket.  Before doing show(),
it then calls lock_sock_fast().

In a machine with ~400k connections, the maximum number of
sk in a bucket of the established hashtable is 7.  0.02% of
the established connections fall into this bucket size.

For listen hash (port+addr lhash2), the bucket is usually very
small also except for the SO_REUSEPORT use case which the
userspace could have one SO_REUSEPORT socket per thread.

While batching is used, it can also minimize the chance of missing
sock in the setsockopt use case if the whole bucket is batched.
This patch will start with a batch array with INIT_BATCH_SZ (16)
which will be enough for the most common cases.  bpf_iter_tcp_batch()
will try to realloc to a larger array to handle exception case (e.g.
the SO_REUSEPORT case in the lhash2).
Signed-off-by: NMartin KaFai Lau <kafai@fb.com>
Signed-off-by: NAndrii Nakryiko <andrii@kernel.org>
Reviewed-by: NEric Dumazet <edumazet@google.com>
Acked-by: NKuniyuki Iwashima <kuniyu@amazon.co.jp>
Acked-by: NYonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/bpf/20210701200613.1036157-1-kafai@fb.com

This patch moves the tcp seq_file iteration on listeners
from the port only listening_hash to the port+addr lhash2.

When iterating from the bpf iter, the next patch will need to
lock the socket such that the bpf iter can call setsockopt (e.g. to
change the TCP_CONGESTION).  To avoid locking the bucket and then locking
the sock, the bpf iter will first batch some sockets from the same bucket
and then unlock the bucket.  If the bucket size is small (which
usually is), it is easier to batch the whole bucket such that it is less
likely to miss a setsockopt on a socket due to changes in the bucket.

However, the port only listening_hash could have many listeners
hashed to a bucket (e.g. many individual VIP(s):443 and also
multiple by the number of SO_REUSEPORT).  We have seen bucket size in
tens of thousands range.  Also, the chance of having changes
in some popular port buckets (e.g. 443) is also high.

The port+addr lhash2 was introduced to solve this large listener bucket
issue.  Also, the listening_hash usage has already been replaced with
lhash2 in the fast path inet[6]_lookup_listener().  This patch follows
the same direction on moving to lhash2 and iterates the lhash2
instead of listening_hash.
Signed-off-by: NMartin KaFai Lau <kafai@fb.com>
Signed-off-by: NAndrii Nakryiko <andrii@kernel.org>
Reviewed-by: NEric Dumazet <edumazet@google.com>
Acked-by: NKuniyuki Iwashima <kuniyu@amazon.co.jp>
Acked-by: NYonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/bpf/20210701200606.1035783-1-kafai@fb.com

The current listening_get_next() is overloaded by passing
NULL to the 2nd arg, like listening_get_next(seq, NULL), to
mean get_first().

This patch moves some logic from the listening_get_next() into
a new function listening_get_first().  It will be equivalent
to the current established_get_first() and established_get_next()
setup.  get_first() is to find a non empty bucket and return
the first sk.  get_next() is to find the next sk of the current
bucket and then resorts to get_first() if the current bucket is
exhausted.

The next patch is to move the listener seq_file iteration from
listening_hash (port only) to lhash2 (port+addr).
Separating out listening_get_first() from listening_get_next()
here will make the following lhash2 changes cleaner and easier to
follow.
Signed-off-by: NMartin KaFai Lau <kafai@fb.com>
Signed-off-by: NAndrii Nakryiko <andrii@kernel.org>
Reviewed-by: NEric Dumazet <edumazet@google.com>
Acked-by: NKuniyuki Iwashima <kuniyu@amazon.co.jp>
Acked-by: NYonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/bpf/20210701200600.1035353-1-kafai@fb.com

A following patch will create a separate struct to store extra
bpf_iter state and it will embed the existing tcp_iter_state like this:
struct bpf_tcp_iter_state {
	struct tcp_iter_state state;
	/* More bpf_iter specific states here ... */
}

As a prep work, this patch removes the
"struct tcp_seq_afinfo *bpf_seq_afinfo" where its purpose is
to tell if it is iterating from bpf_iter instead of proc fs.
Currently, if "*bpf_seq_afinfo" is not NULL, it is iterating from
bpf_iter.  The kernel should not filter by the addr family and
leave this filtering decision to the bpf prog.

Instead of adding a "*bpf_seq_afinfo" pointer, this patch uses the
"seq->op == &bpf_iter_tcp_seq_ops" test to tell if it is iterating
from the bpf iter.

The bpf_iter_(init|fini)_tcp() is left here to prepare for
the change of a following patch.
Signed-off-by: NMartin KaFai Lau <kafai@fb.com>
Signed-off-by: NAndrii Nakryiko <andrii@kernel.org>
Reviewed-by: NEric Dumazet <edumazet@google.com>
Acked-by: NKuniyuki Iwashima <kuniyu@amazon.co.jp>
Acked-by: NYonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/bpf/20210701200554.1034982-1-kafai@fb.com

This patch refactors the net and family matching into
two new helpers, seq_sk_match() and seq_file_family().

seq_file_family() is in the later part of the file to prepare
the change of a following patch.
Signed-off-by: NMartin KaFai Lau <kafai@fb.com>
Signed-off-by: NAndrii Nakryiko <andrii@kernel.org>
Reviewed-by: NEric Dumazet <edumazet@google.com>
Acked-by: NKuniyuki Iwashima <kuniyu@amazon.co.jp>
Acked-by: NYonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/bpf/20210701200548.1034629-1-kafai@fb.com

st->bucket stores the current bucket number.
st->offset stores the offset within this bucket that is the sk to be
seq_show().  Thus, st->offset only makes sense within the same
st->bucket.

These two variables are an optimization for the common no-lseek case.
When resuming the seq_file iteration (i.e. seq_start()),
tcp_seek_last_pos() tries to continue from the st->offset
at bucket st->bucket.

However, it is possible that the bucket pointed by st->bucket
has changed and st->offset may end up skipping the whole st->bucket
without finding a sk.  In this case, tcp_seek_last_pos() currently
continues to satisfy the offset condition in the next (and incorrect)
bucket.  Instead, regardless of the offset value, the first sk of the
next bucket should be returned.  Thus, "bucket == st->bucket" check is
added to tcp_seek_last_pos().

The chance of hitting this is small and the issue is a decade old,
so targeting for the next tree.

Fixes: a8b690f9 ("tcp: Fix slowness in read /proc/net/tcp")
Signed-off-by: NMartin KaFai Lau <kafai@fb.com>
Signed-off-by: NAndrii Nakryiko <andrii@kernel.org>
Reviewed-by: NEric Dumazet <edumazet@google.com>
Acked-by: NKuniyuki Iwashima <kuniyu@amazon.co.jp>
Acked-by: NYonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/bpf/20210701200541.1033917-1-kafai@fb.com

While tp->mtu_info is read while socket is owned, the write
sides happen from err handlers (tcp_v[46]_mtu_reduced)
which only own the socket spinlock.

Fixes: 563d34d0 ("tcp: dont drop MTU reduction indications")
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch introduces a function wrapper to call the sk_error_report
callback. That will prepare to add additional handling whenever
sk_error_report is called, for example to trace socket errors.
Signed-off-by: NAlexander Aring <aahringo@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch also changes the code to call reuseport_migrate_sock() and
inet_reqsk_clone(), but unlike the other cases, we do not call
inet_reqsk_clone() right after reuseport_migrate_sock().

Currently, in the receive path for TCP_NEW_SYN_RECV sockets, its listener
has three kinds of refcnt:

  (A) for listener itself
  (B) carried by reuqest_sock
  (C) sock_hold() in tcp_v[46]_rcv()

While processing the req, (A) may disappear by close(listener). Also, (B)
can disappear by accept(listener) once we put the req into the accept
queue. So, we have to hold another refcnt (C) for the listener to prevent
use-after-free.

For socket migration, we call reuseport_migrate_sock() to select a listener
with (A) and to increment the new listener's refcnt in tcp_v[46]_rcv().
This refcnt corresponds to (C) and is cleaned up later in tcp_v[46]_rcv().
Thus we have to take another refcnt (B) for the newly cloned request_sock.

In inet_csk_complete_hashdance(), we hold the count (B), clone the req, and
try to put the new req into the accept queue. By migrating req after
winning the "own_req" race, we can avoid such a worst situation:

  CPU 1 looks up req1
  CPU 2 looks up req1, unhashes it, then CPU 1 loses the race
  CPU 3 looks up req2, unhashes it, then CPU 2 loses the race
  ...
Signed-off-by: NKuniyuki Iwashima <kuniyu@amazon.co.jp>
Signed-off-by: NDaniel Borkmann <daniel@iogearbox.net>
Reviewed-by: NEric Dumazet <edumazet@google.com>
Acked-by: NMartin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20210612123224.12525-8-kuniyu@amazon.co.jp

Add a tracepoint for capturing TCP segments with
a bad checksum. This makes it easy to identify
sources of bad frames in the fleet (e.g. machines
with faulty NICs).

It should also help tools like IOvisor's tcpdrop.py
which are used today to get detailed information
about such packets.

We don't have a socket in many cases so we must
open code the address extraction based just on
the skb.

v2: add missing export for ipv6=m
Signed-off-by: NJakub Kicinski <kuba@kernel.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The MPTCP reset option allows to carry a mptcp-specific error code that
provides more information on the nature of a connection reset.

Reset option data received gets stored in the subflow context so it can
be sent to userspace via the 'subflow closed' netlink event.

When a subflow is closed, the desired error code that should be sent to
the peer is also placed in the subflow context structure.

If a reset is sent before subflow establishment could complete, e.g. on
HMAC failure during an MP_JOIN operation, the mptcp skb extension is
used to store the reset information.
Signed-off-by: NFlorian Westphal <fw@strlen.de>
Signed-off-by: NMat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Currently sockmap calls into each protocol to update the struct
proto and replace it. This certainly won't work when the protocol
is implemented as a module, for example, AF_UNIX.

Introduce a new ops sk->sk_prot->psock_update_sk_prot(), so each
protocol can implement its own way to replace the struct proto.
This also helps get rid of symbol dependencies on CONFIG_INET.
Signed-off-by: NCong Wang <cong.wang@bytedance.com>
Signed-off-by: NAlexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210331023237.41094-11-xiyou.wangcong@gmail.com

This patch avoids the indirect call for the common case:
ip6_dst_check and ipv4_dst_check
Signed-off-by: NBrian Vazquez <brianvv@google.com>
Signed-off-by: NJakub Kicinski <kuba@kernel.org>

Add custom implementation of getsockopt hook for TCP_ZEROCOPY_RECEIVE.
We skip generic hooks for TCP_ZEROCOPY_RECEIVE and have a custom
call in do_tcp_getsockopt using the on-stack data. This removes
3% overhead for locking/unlocking the socket.

Without this patch:
     3.38%     0.07%  tcp_mmap  [kernel.kallsyms]  [k] __cgroup_bpf_run_filter_getsockopt
            |
             --3.30%--__cgroup_bpf_run_filter_getsockopt
                       |
                        --0.81%--__kmalloc

With the patch applied:
     0.52%     0.12%  tcp_mmap  [kernel.kallsyms]  [k] __cgroup_bpf_run_filter_getsockopt_kern

Note, exporting uapi/tcp.h requires removing netinet/tcp.h
from test_progs.h because those headers have confliciting
definitions.
Signed-off-by: NStanislav Fomichev <sdf@google.com>
Signed-off-by: NAlexei Starovoitov <ast@kernel.org>
Acked-by: NMartin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20210115163501.805133-2-sdf@google.com

Receiving ACK with a valid SYN cookie, cookie_v4_check() allocates struct
request_sock and then can allocate inet_rsk(req)->ireq_opt. After that,
tcp_v4_syn_recv_sock() allocates struct sock and copies ireq_opt to
inet_sk(sk)->inet_opt. Normally, tcp_v4_syn_recv_sock() inserts the full
socket into ehash and sets NULL to ireq_opt. Otherwise,
tcp_v4_syn_recv_sock() has to reset inet_opt by NULL and free the full
socket.

The commit 01770a16 ("tcp: fix race condition when creating child
sockets from syncookies") added a new path, in which more than one cores
create full sockets for the same SYN cookie. Currently, the core which
loses the race frees the full socket without resetting inet_opt, resulting
in that both sock_put() and reqsk_put() call kfree() for the same memory:

  sock_put
    sk_free
      __sk_free
        sk_destruct
          __sk_destruct
            sk->sk_destruct/inet_sock_destruct
              kfree(rcu_dereference_protected(inet->inet_opt, 1));

  reqsk_put
    reqsk_free
      __reqsk_free
        req->rsk_ops->destructor/tcp_v4_reqsk_destructor
          kfree(rcu_dereference_protected(inet_rsk(req)->ireq_opt, 1));

Calling kmalloc() between the double kfree() can lead to use-after-free, so
this patch fixes it by setting NULL to inet_opt before sock_put().

As a side note, this kind of issue does not happen for IPv6. This is
because tcp_v6_syn_recv_sock() clones both ipv6_opt and pktopts which
correspond to ireq_opt in IPv4.

Fixes: 01770a16 ("tcp: fix race condition when creating child sockets from syncookies")
CC: Ricardo Dias <rdias@singlestore.com>
Signed-off-by: NKuniyuki Iwashima <kuniyu@amazon.co.jp>
Reviewed-by: NBenjamin Herrenschmidt <benh@amazon.com>
Reviewed-by: NEric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20210118055920.82516-1-kuniyu@amazon.co.jpSigned-off-by: NJakub Kicinski <kuba@kernel.org>

Heiner Kallweit reported that some skbs were sent with
the following invalid GSO properties :
- gso_size > 0
- gso_type == 0

This was triggerring a WARN_ON_ONCE() in rtl8169_tso_csum_v2.

Juerg Haefliger was able to reproduce a similar issue using
a lan78xx NIC and a workload mixing TCP incoming traffic
and forwarded packets.

The problem is that tcp_add_backlog() is writing
over gso_segs and gso_size even if the incoming packet will not
be coalesced to the backlog tail packet.

While skb_try_coalesce() would bail out if tail packet is cloned,
this overwriting would lead to corruptions of other packets
cooked by lan78xx, sharing a common super-packet.

The strategy used by lan78xx is to use a big skb, and split
it into all received packets using skb_clone() to avoid copies.
The drawback of this strategy is that all the small skb share a common
struct skb_shared_info.

This patch rewrites TCP gso_size/gso_segs handling to only
happen on the tail skb, since skb_try_coalesce() made sure
it was not cloned.

Fixes: 4f693b55 ("tcp: implement coalescing on backlog queue")
Signed-off-by: NEric Dumazet <edumazet@google.com>
Bisected-by: NJuerg Haefliger <juergh@canonical.com>
Tested-by: NJuerg Haefliger <juergh@canonical.com>
Reported-by: NHeiner Kallweit <hkallweit1@gmail.com>
Link: https://bugzilla.kernel.org/show_bug.cgi?id=209423
Link: https://lore.kernel.org/r/20210119164900.766957-1-eric.dumazet@gmail.comSigned-off-by: NJakub Kicinski <kuba@kernel.org>

For DCTCP, we have to retain the ECT bits set by the congestion control
algorithm on the socket when reflecting syn TOS in syn-ack, in order to
make ECN work properly.

Fixes: ac8f1710 ("tcp: reflect tos value received in SYN to the socket")
Reported-by: NAlexander Duyck <alexanderduyck@fb.com>
Signed-off-by: NWei Wang <weiwan@google.com>
Reviewed-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The Multipath-TCP standard (RFC 8684) says that an MPTCP host should send
a TCP reset if the token in a MP_JOIN request is unknown.

At this time we don't do this, the 3whs completes and the 'new subflow'
is reset afterwards.  There are two ways to allow MPTCP to send the
reset.

1. override 'send_synack' callback and emit the rst from there.
   The drawback is that the request socket gets inserted into the
   listeners queue just to get removed again right away.

2. Send the reset from the 'route_req' function instead.
   This avoids the 'add&remove request socket', but route_req lacks the
   skb that is required to send the TCP reset.

Instead of just adding the skb to that function for MPTCP sake alone,
Paolo suggested to merge init_req and route_req functions.

This saves one indirection from syn processing path and provides the skb
to the merged function at the same time.

'send reset on unknown mptcp join token' is added in next patch.
Suggested-by: NPaolo Abeni <pabeni@redhat.com>
Cc: Eric Dumazet <edumazet@google.com>
Signed-off-by: NFlorian Westphal <fw@strlen.de>
Signed-off-by: NJakub Kicinski <kuba@kernel.org>

When a BPF program is used to select between a type of TCP congestion
control algorithm that uses either ECN or not there is a case where the
synack for the frame was coming up without the ECT0 bit set. A bit of
research found that this was due to the final socket being configured to
dctcp while the listener socket was staying in cubic.

To reproduce it all that is needed is to monitor TCP traffic while running
the sample bpf program "samples/bpf/tcp_cong_kern.c". What is observed,
assuming tcp_dctcp module is loaded or compiled in and the traffic matches
the rules in the sample file, is that for all frames with the exception of
the synack the ECT0 bit is set.

To address that it is necessary to make one additional call to
tcp_bpf_ca_needs_ecn using the request socket and then use the output of
that to set the ECT0 bit for the tos/tclass of the packet.

Fixes: 91b5b21c ("bpf: Add support for changing congestion control")
Signed-off-by: NAlexander Duyck <alexanderduyck@fb.com>
Link: https://lore.kernel.org/r/160593039663.2604.1374502006916871573.stgit@localhost.localdomainSigned-off-by: NJakub Kicinski <kuba@kernel.org>

When the TCP stack is in SYN flood mode, the server child socket is
created from the SYN cookie received in a TCP packet with the ACK flag
set.

The child socket is created when the server receives the first TCP
packet with a valid SYN cookie from the client. Usually, this packet
corresponds to the final step of the TCP 3-way handshake, the ACK
packet. But is also possible to receive a valid SYN cookie from the
first TCP data packet sent by the client, and thus create a child socket
from that SYN cookie.

Since a client socket is ready to send data as soon as it receives the
SYN+ACK packet from the server, the client can send the ACK packet (sent
by the TCP stack code), and the first data packet (sent by the userspace
program) almost at the same time, and thus the server will equally
receive the two TCP packets with valid SYN cookies almost at the same
instant.

When such event happens, the TCP stack code has a race condition that
occurs between the momement a lookup is done to the established
connections hashtable to check for the existence of a connection for the
same client, and the moment that the child socket is added to the
established connections hashtable. As a consequence, this race condition
can lead to a situation where we add two child sockets to the
established connections hashtable and deliver two sockets to the
userspace program to the same client.

This patch fixes the race condition by checking if an existing child
socket exists for the same client when we are adding the second child
socket to the established connections socket. If an existing child
socket exists, we drop the packet and discard the second child socket
to the same client.
Signed-off-by: NRicardo Dias <rdias@singlestore.com>
Signed-off-by: NEric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20201120111133.GA67501@rdias-suse-pc.lanSigned-off-by: NJakub Kicinski <kuba@kernel.org>

An issue was recently found where DCTCP SYN/ACK packets did not have the
ECT bit set in the L3 header. A bit of code review found that the recent
change referenced below had gone though and added a mask that prevented the
ECN bits from being populated in the L3 header.

This patch addresses that by rolling back the mask so that it is only
applied to the flags coming from the incoming TCP request instead of
applying it to the socket tos/tclass field. Doing this the ECT bits were
restored in the SYN/ACK packets in my testing.

One thing that is not addressed by this patch set is the fact that
tcp_reflect_tos appears to be incompatible with ECN based congestion
avoidance algorithms. At a minimum the feature should likely be documented
which it currently isn't.

Fixes: ac8f1710 ("tcp: reflect tos value received in SYN to the socket")
Signed-off-by: NAlexander Duyck <alexanderduyck@fb.com>
Acked-by: NWei Wang <weiwan@google.com>
Signed-off-by: NJakub Kicinski <kuba@kernel.org>

Both IPv4 and IPv6 needs it via a function pointer.
Following patch will avoid the indirect call.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NJakub Kicinski <kuba@kernel.org>

We got reports from GKE customers flows being reset by netfilter
conntrack unless nf_conntrack_tcp_be_liberal is set to 1.

Traces seemed to suggest ACK packet being dropped by the
packet capture, or more likely that ACK were received in the
wrong order.

 wscale=7, SYN and SYNACK not shown here.

 This ACK allows the sender to send 1871*128 bytes from seq 51359321 :
 New right edge of the window -> 51359321+1871*128=51598809

 09:17:23.389210 IP A > B: Flags [.], ack 51359321, win 1871, options [nop,nop,TS val 10 ecr 999], length 0

 09:17:23.389212 IP B > A: Flags [.], seq 51422681:51424089, ack 1577, win 268, options [nop,nop,TS val 999 ecr 10], length 1408
 09:17:23.389214 IP A > B: Flags [.], ack 51422681, win 1376, options [nop,nop,TS val 10 ecr 999], length 0
 09:17:23.389253 IP B > A: Flags [.], seq 51424089:51488857, ack 1577, win 268, options [nop,nop,TS val 999 ecr 10], length 64768
 09:17:23.389272 IP A > B: Flags [.], ack 51488857, win 859, options [nop,nop,TS val 10 ecr 999], length 0
 09:17:23.389275 IP B > A: Flags [.], seq 51488857:51521241, ack 1577, win 268, options [nop,nop,TS val 999 ecr 10], length 32384

 Receiver now allows to send 606*128=77568 from seq 51521241 :
 New right edge of the window -> 51521241+606*128=51598809

 09:17:23.389296 IP A > B: Flags [.], ack 51521241, win 606, options [nop,nop,TS val 10 ecr 999], length 0

 09:17:23.389308 IP B > A: Flags [.], seq 51521241:51553625, ack 1577, win 268, options [nop,nop,TS val 999 ecr 10], length 32384

 It seems the sender exceeds RWIN allowance, since 51611353 > 51598809

 09:17:23.389346 IP B > A: Flags [.], seq 51553625:51611353, ack 1577, win 268, options [nop,nop,TS val 999 ecr 10], length 57728
 09:17:23.389356 IP B > A: Flags [.], seq 51611353:51618393, ack 1577, win 268, options [nop,nop,TS val 999 ecr 10], length 7040

 09:17:23.389367 IP A > B: Flags [.], ack 51611353, win 0, options [nop,nop,TS val 10 ecr 999], length 0

 netfilter conntrack is not happy and sends RST

 09:17:23.389389 IP A > B: Flags [R], seq 92176528, win 0, length 0
 09:17:23.389488 IP B > A: Flags [R], seq 174478967, win 0, length 0

 Now imagine ACK were delivered out of order and tcp_add_backlog() sets window based on wrong packet.
 New right edge of the window -> 51521241+859*128=51631193

Normally TCP stack handles OOO packets just fine, but it
turns out tcp_add_backlog() does not. It can update the window
field of the aggregated packet even if the ACK sequence
of the last received packet is too old.

Many thanks to Alexandre Ferrieux for independently reporting the issue
and suggesting a fix.

Fixes: 4f693b55 ("tcp: implement coalescing on backlog queue")
Signed-off-by: NEric Dumazet <edumazet@google.com>
Reported-by: NAlexandre Ferrieux <alexandre.ferrieux@orange.com>
Acked-by: NSoheil Hassas Yeganeh <soheil@google.com>
Acked-by: NNeal Cardwell <ncardwell@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This commit adds a new TCP feature to reflect the tos value received in
SYN, and send it out on the SYN-ACK, and eventually set the tos value of
the established socket with this reflected tos value. This provides a
way to set the traffic class/QoS level for all traffic in the same
connection to be the same as the incoming SYN request. It could be
useful in data centers to provide equivalent QoS according to the
incoming request.
This feature is guarded by /proc/sys/net/ipv4/tcp_reflect_tos, and is by
default turned off.
Signed-off-by: NWei Wang <weiwan@google.com>
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This commit adds tos as a new passed in parameter to
ip_build_and_send_pkt() which will be used in the later commit.
This is a pure restructure and does not have any functional change.
Signed-off-by: NWei Wang <weiwan@google.com>
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Drop duplicate words in comments in net/ipv4/.
Signed-off-by: NRandy Dunlap <rdunlap@infradead.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The bpf prog needs to parse the SYN header to learn what options have
been sent by the peer's bpf-prog before writing its options into SYNACK.
This patch adds a "syn_skb" arg to tcp_make_synack() and send_synack().
This syn_skb will eventually be made available (as read-only) to the
bpf prog.  This will be the only SYN packet available to the bpf
prog during syncookie.  For other regular cases, the bpf prog can
also use the saved_syn.

When writing options, the bpf prog will first be called to tell the
kernel its required number of bytes.  It is done by the new
bpf_skops_hdr_opt_len().  The bpf prog will only be called when the new
BPF_SOCK_OPS_WRITE_HDR_OPT_CB_FLAG is set in tp->bpf_sock_ops_cb_flags.
When the bpf prog returns, the kernel will know how many bytes are needed
and then update the "*remaining" arg accordingly.  4 byte alignment will
be included in the "*remaining" before this function returns.  The 4 byte
aligned number of bytes will also be stored into the opts->bpf_opt_len.
"bpf_opt_len" is a newly added member to the struct tcp_out_options.

Then the new bpf_skops_write_hdr_opt() will call the bpf prog to write the
header options.  The bpf prog is only called if it has reserved spaces
before (opts->bpf_opt_len > 0).

The bpf prog is the last one getting a chance to reserve header space
and writing the header option.

These two functions are half implemented to highlight the changes in
TCP stack.  The actual codes preparing the bpf running context and
invoking the bpf prog will be added in the later patch with other
necessary bpf pieces.
Signed-off-by: NMartin KaFai Lau <kafai@fb.com>
Signed-off-by: NAlexei Starovoitov <ast@kernel.org>
Reviewed-by: NEric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/bpf/20200820190052.2885316-1-kafai@fb.com

This patch refactored target bpf_iter_init_seq_priv_t callback
function to accept additional information. This will be needed
in later patches for map element targets since a particular
map should be passed to traverse elements for that particular
map. In the future, other information may be passed to target
as well, e.g., pid, cgroup id, etc. to customize the iterator.
Signed-off-by: NYonghong Song <yhs@fb.com>
Signed-off-by: NAlexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200723184110.590156-1-yhs@fb.com

There is no functionality change for this patch.
Struct bpf_iter_reg is used to register a bpf_iter target,
which includes information for both prog_load, link_create
and seq_file creation.

This patch puts fields related seq_file creation into
a different structure. This will be useful for map
elements iterator where one iterator covers different
map types and different map types may have different
seq_ops, init/fini private_data function and
private_data size.
Signed-off-by: NYonghong Song <yhs@fb.com>
Signed-off-by: NAlexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200723184109.590030-1-yhs@fb.com

Pass a sockptr_t to prepare for set_fs-less handling of the kernel
pointer from bpf-cgroup.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

One additional field btf_id is added to struct
bpf_ctx_arg_aux to store the precomputed btf_ids.
The btf_id is computed at build time with
BTF_ID_LIST or BTF_ID_LIST_GLOBAL macro definitions.
All existing bpf iterators are changed to used
pre-compute btf_ids.
Signed-off-by: NYonghong Song <yhs@fb.com>
Signed-off-by: NAlexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200720163403.1393551-1-yhs@fb.com

Handle the few cases that need special treatment in-line using
in_compat_syscall().  This also removes all the now unused
compat_{get,set}sockopt methods.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Handle the few cases that need special treatment in-line using
in_compat_syscall().
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

My prior fix went a bit too far, according to Herbert and Mathieu.

Since we accept that concurrent TCP MD5 lookups might see inconsistent
keys, we can use READ_ONCE()/WRITE_ONCE() instead of smp_rmb()/smp_wmb()

Clearing all key->key[] is needed to avoid possible KMSAN reports,
if key->keylen is increased. Since tcp_md5_do_add() is not fast path,
using __GFP_ZERO to clear all struct tcp_md5sig_key is simpler.

data_race() was added in linux-5.8 and will prevent KCSAN reports,
this can safely be removed in stable backports, if data_race() is
not yet backported.

v2: use data_race() both in tcp_md5_hash_key() and tcp_md5_do_add()

Fixes: 6a2febec ("tcp: md5: add missing memory barriers in tcp_md5_do_add()/tcp_md5_hash_key()")
Signed-off-by: NEric Dumazet <edumazet@google.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: Marco Elver <elver@google.com>
Reviewed-by: NMathieu Desnoyers <mathieu.desnoyers@efficios.com>
Acked-by: NHerbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

MD5 keys are read with RCU protection, and tcp_md5_do_add()
might update in-place a prior key.

Normally, typical RCU updates would allocate a new piece
of memory. In this case only key->key and key->keylen might
be updated, and we do not care if an incoming packet could
see the old key, the new one, or some intermediate value,
since changing the key on a live flow is known to be problematic
anyway.

We only want to make sure that in the case key->keylen
is changed, cpus in tcp_md5_hash_key() wont try to use
uninitialized data, or crash because key->keylen was
read twice to feed sg_init_one() and ahash_request_set_crypt()

Fixes: 9ea88a15 ("tcp: md5: check md5 signature without socket lock")
Signed-off-by: NEric Dumazet <edumazet@google.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The bpf iterator for tcp is implemented. Both tcp4 and tcp6
sockets will be traversed. It is up to bpf program to
filter for tcp4 or tcp6 only, or both families of sockets.
Signed-off-by: NYonghong Song <yhs@fb.com>
Signed-off-by: NAlexei Starovoitov <ast@kernel.org>
Acked-by: NMartin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20200623230805.3987959-1-yhs@fb.com

A new field bpf_seq_afinfo is added to tcp_iter_state
to provide bpf tcp iterator afinfo. There are two
reasons on why we did this.

First, the current way to get afinfo from PDE_DATA
does not work for bpf iterator as its seq_file
inode does not conform to /proc/net/{tcp,tcp6}
inode structures. More specifically, anonymous
bpf iterator will use an anonymous inode which
is shared in the system and we cannot change inode
private data structure at all.

Second, bpf iterator for tcp/tcp6 wants to
traverse all tcp and tcp6 sockets in one pass
and bpf program can control whether they want
to skip one sk_family or not. Having a different
afinfo with family AF_UNSPEC make it easier
to understand in the code.

This patch does not change /proc/net/{tcp,tcp6} behavior
as the bpf_seq_afinfo will be NULL for these two proc files.
Signed-off-by: NYonghong Song <yhs@fb.com>
Signed-off-by: NAlexei Starovoitov <ast@kernel.org>
Acked-by: NMartin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20200623230804.3987829-1-yhs@fb.com

Make tcp_ld_RTO_revert() helper available to IPv6, and
implement RFC 6069 :

Quoting this RFC :

3. Connectivity Disruption Indication

   For Internet Protocol version 6 (IPv6) [RFC2460], the counterpart of
   the ICMP destination unreachable message of code 0 (net unreachable)
   and of code 1 (host unreachable) is the ICMPv6 destination
   unreachable message of code 0 (no route to destination) [RFC4443].
   As with IPv4, a router should generate an ICMPv6 destination
   unreachable message of code 0 in response to a packet that cannot be
   delivered to its destination address because it lacks a matching
   entry in its routing table.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Acked-by: NYuchung Cheng <ycheng@google.com>
Acked-by: NNeal Cardwell <ncardwell@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This essentially reverts 4d1a2d9e ("Revert Backoff [v3]:
Rename skb to icmp_skb in tcp_v4_err()")

Now we have tcp_ld_RTO_revert() helper, we can use the usual
name for sk_buff parameter, so that tcp_v4_err() and
tcp_v6_err() use similar names.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Acked-by: NNeal Cardwell <ncardwell@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>