Back when tcp_tso_autosize() and TCP pacing were introduced,
our focus was really to reduce burst sizes for long distance
flows.
The simple heuristic of using sk_pacing_rate/1024 has worked
well, but can lead to too small packets for hosts in the same
rack/cluster, when thousands of flows compete for the bottleneck.
Neal Cardwell had the idea of making the TSO burst size
a function of both sk_pacing_rate and tcp_min_rtt()
Indeed, for local flows, sending bigger bursts is better
to reduce cpu costs, as occasional losses can be repaired
quite fast.
This patch is based on Neal Cardwell implementation
done more than two years ago.
bbr is adjusting max_pacing_rate based on measured bandwidth,
while cubic would over estimate max_pacing_rate.
/proc/sys/net/ipv4/tcp_tso_rtt_log can be used to tune or disable
this new feature, in logarithmic steps.
Tested:
100Gbit NIC, two hosts in the same rack, 4K MTU.
600 flows rate-limited to 20000000 bytes per second.
Before patch: (TSO sizes would be limited to 20000000/1024/4096 -> 4 segments per TSO)
~# echo 0 >/proc/sys/net/ipv4/tcp_tso_rtt_log
~# nstat -n;perf stat ./super_netperf 600 -H otrv6 -l 20 -- -K dctcp -q 20000000;nstat|egrep "TcpInSegs|TcpOutSegs|TcpRetransSegs|Delivered"
96005
Performance counter stats for './super_netperf 600 -H otrv6 -l 20 -- -K dctcp -q 20000000':
65,945.29 msec task-clock # 2.845 CPUs utilized
1,314,632 context-switches # 19935.279 M/sec
5,292 cpu-migrations # 80.249 M/sec
940,641 page-faults # 14264.023 M/sec
201,117,030,926 cycles # 3049769.216 GHz (83.45%)
17,699,435,405 stalled-cycles-frontend # 8.80% frontend cycles idle (83.48%)
136,584,015,071 stalled-cycles-backend # 67.91% backend cycles idle (83.44%)
53,809,530,436 instructions # 0.27 insn per cycle
# 2.54 stalled cycles per insn (83.36%)
9,062,315,523 branches # 137422329.563 M/sec (83.22%)
153,008,621 branch-misses # 1.69% of all branches (83.32%)
23.182970846 seconds time elapsed
TcpInSegs 15648792 0.0
TcpOutSegs 58659110 0.0 # Average of 3.7 4K segments per TSO packet
TcpExtTCPDelivered 58654791 0.0
TcpExtTCPDeliveredCE 19 0.0
After patch:
~# echo 9 >/proc/sys/net/ipv4/tcp_tso_rtt_log
~# nstat -n;perf stat ./super_netperf 600 -H otrv6 -l 20 -- -K dctcp -q 20000000;nstat|egrep "TcpInSegs|TcpOutSegs|TcpRetransSegs|Delivered"
96046
Performance counter stats for './super_netperf 600 -H otrv6 -l 20 -- -K dctcp -q 20000000':
48,982.58 msec task-clock # 2.104 CPUs utilized
186,014 context-switches # 3797.599 M/sec
3,109 cpu-migrations # 63.472 M/sec
941,180 page-faults # 19214.814 M/sec
153,459,763,868 cycles # 3132982.807 GHz (83.56%)
12,069,861,356 stalled-cycles-frontend # 7.87% frontend cycles idle (83.32%)
120,485,917,953 stalled-cycles-backend # 78.51% backend cycles idle (83.24%)
36,803,672,106 instructions # 0.24 insn per cycle
# 3.27 stalled cycles per insn (83.18%)
5,947,266,275 branches # 121417383.427 M/sec (83.64%)
87,984,616 branch-misses # 1.48% of all branches (83.43%)
23.281200256 seconds time elapsed
TcpInSegs 1434706 0.0
TcpOutSegs 58883378 0.0 # Average of 41 4K segments per TSO packet
TcpExtTCPDelivered 58878971 0.0
TcpExtTCPDeliveredCE 9664 0.0
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Neal Cardwell <ncardwell@google.com>
Link: https://lore.kernel.org/r/20220309015757.2532973-1-eric.dumazet@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
We have a number of cases where function returns drop/no drop
decision as a boolean. Now that we want to report the reason
code as well we have to pass extra output arguments.
We can make the reason code evaluate correctly as bool.
I believe we're good to reorder the reasons as they are
reported to user space as strings.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
The functions do essentially the same work to verify TCP-MD5 sign.
Code can be merged into one family-independent function in order to
reduce copy'n'paste and generated code.
Later with TCP-AO option added, this will allow to create one function
that's responsible for segment verification, that will have all the
different checks for MD5/AO/non-signed packets, which in turn will help
to see checks for all corner-cases in one function, rather than spread
around different families and functions.
Cc: Eric Dumazet <edumazet@google.com>
Cc: Hideaki YOSHIFUJI <yoshfuji@linux-ipv6.org>
Signed-off-by: Dmitry Safonov <dima@arista.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/r/20220223175740.452397-1-dima@arista.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Replace kfree_skb() used in tcp_v4_do_rcv() and tcp_v6_do_rcv() 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: Eric Dumazet <edumazet@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Pass the address of drop_reason to tcp_add_backlog() to store the
reasons for skb drops when fails. Following drop reasons are
introduced:
SKB_DROP_REASON_SOCKET_BACKLOG
Reviewed-by: Mengen Sun <mengensun@tencent.com>
Reviewed-by: Hao Peng <flyingpeng@tencent.com>
Signed-off-by: Menglong Dong <imagedong@tencent.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Pass the address of drop reason to tcp_v4_inbound_md5_hash() and
tcp_v6_inbound_md5_hash() to store the reasons for skb drops when this
function fails. Therefore, the drop reason can be passed to
kfree_skb_reason() when the skb needs to be freed.
Following drop reasons are added:
SKB_DROP_REASON_TCP_MD5NOTFOUND
SKB_DROP_REASON_TCP_MD5UNEXPECTED
SKB_DROP_REASON_TCP_MD5FAILURE
SKB_DROP_REASON_TCP_MD5* above correspond to LINUX_MIB_TCPMD5*
Reviewed-by: Mengen Sun <mengensun@tencent.com>
Reviewed-by: Hao Peng <flyingpeng@tencent.com>
Signed-off-by: Menglong Dong <imagedong@tencent.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Use kfree_skb_reason() for some path in tcp_v4_rcv() that missed before,
including:
SKB_DROP_REASON_SOCKET_FILTER
SKB_DROP_REASON_XFRM_POLICY
Reviewed-by: Mengen Sun <mengensun@tencent.com>
Reviewed-by: Hao Peng <flyingpeng@tencent.com>
Signed-off-by: Menglong Dong <imagedong@tencent.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Current release - new code bugs:
- tcp: add a missing sk_defer_free_flush() in tcp_splice_read()
- tcp: add a stub for sk_defer_free_flush(), fix CONFIG_INET=n
- nf_tables: set last expression in register tracking area
- nft_connlimit: fix memleak if nf_ct_netns_get() fails
- mptcp: fix removing ids bitmap setting
- bonding: use rcu_dereference_rtnl when getting active slave
- fix three cases of sleep in atomic context in drivers: lan966x, gve
- handful of build fixes for esoteric drivers after netdev->dev_addr
was made const
Previous releases - regressions:
- revert "ipv6: Honor all IPv6 PIO Valid Lifetime values", it broke
Linux compatibility with USGv6 tests
- procfs: show net device bound packet types
- ipv4: fix ip option filtering for locally generated fragments
- phy: broadcom: hook up soft_reset for BCM54616S
Previous releases - always broken:
- ipv4: raw: lock the socket in raw_bind()
- ipv4: decrease the use of shared IPID generator to decrease the
chance of attackers guessing the values
- procfs: fix cross-netns information leakage in /proc/net/ptype
- ethtool: fix link extended state for big endian
- bridge: vlan: fix single net device option dumping
- ping: fix the sk_bound_dev_if match in ping_lookup
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
-----BEGIN PGP SIGNATURE-----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=mwR3
-----END PGP SIGNATURE-----
Merge tag 'net-5.17-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
Pull networking fixes from Jakub Kicinski:
"Including fixes from netfilter and can.
Current release - new code bugs:
- tcp: add a missing sk_defer_free_flush() in tcp_splice_read()
- tcp: add a stub for sk_defer_free_flush(), fix CONFIG_INET=n
- nf_tables: set last expression in register tracking area
- nft_connlimit: fix memleak if nf_ct_netns_get() fails
- mptcp: fix removing ids bitmap setting
- bonding: use rcu_dereference_rtnl when getting active slave
- fix three cases of sleep in atomic context in drivers: lan966x, gve
- handful of build fixes for esoteric drivers after netdev->dev_addr
was made const
Previous releases - regressions:
- revert "ipv6: Honor all IPv6 PIO Valid Lifetime values", it broke
Linux compatibility with USGv6 tests
- procfs: show net device bound packet types
- ipv4: fix ip option filtering for locally generated fragments
- phy: broadcom: hook up soft_reset for BCM54616S
Previous releases - always broken:
- ipv4: raw: lock the socket in raw_bind()
- ipv4: decrease the use of shared IPID generator to decrease the
chance of attackers guessing the values
- procfs: fix cross-netns information leakage in /proc/net/ptype
- ethtool: fix link extended state for big endian
- bridge: vlan: fix single net device option dumping
- ping: fix the sk_bound_dev_if match in ping_lookup"
* tag 'net-5.17-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (86 commits)
net: bridge: vlan: fix memory leak in __allowed_ingress
net: socket: rename SKB_DROP_REASON_SOCKET_FILTER
ipv4: remove sparse error in ip_neigh_gw4()
ipv4: avoid using shared IP generator for connected sockets
ipv4: tcp: send zero IPID in SYNACK messages
ipv4: raw: lock the socket in raw_bind()
MAINTAINERS: add missing IPv4/IPv6 header paths
MAINTAINERS: add more files to eth PHY
net: stmmac: dwmac-sun8i: use return val of readl_poll_timeout()
net: bridge: vlan: fix single net device option dumping
net: stmmac: skip only stmmac_ptp_register when resume from suspend
net: stmmac: configure PTP clock source prior to PTP initialization
Revert "ipv6: Honor all IPv6 PIO Valid Lifetime values"
connector/cn_proc: Use task_is_in_init_pid_ns()
pid: Introduce helper task_is_in_init_pid_ns()
gve: Fix GFP flags when allocing pages
net: lan966x: Fix sleep in atomic context when updating MAC table
net: lan966x: Fix sleep in atomic context when injecting frames
ethernet: seeq/ether3: don't write directly to netdev->dev_addr
ethernet: 8390/etherh: don't write directly to netdev->dev_addr
...
Rename SKB_DROP_REASON_SOCKET_FILTER, which is used
as the reason of skb drop out of socket filter before
it's part of a released kernel. It will be used for
more protocols than just TCP in future series.
Signed-off-by: Menglong Dong <imagedong@tencent.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/all/20220127091308.91401-2-imagedong@tencent.com/
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
TCP ipv4 uses per-cpu/per-netns ctl sockets in order to send
RST and some ACK packets (on behalf of TIMEWAIT sockets).
This adds memory and cpu costs, which do not seem needed.
Now typical servers have 256 or more cores, this adds considerable
tax to netns users.
tcp sockets are used from BH context, are not receiving packets,
and do not store any persistent state but the 'struct net' pointer
in order to be able to use IPv4 output functions.
Note that I attempted a related change in the past, that had
to be hot-fixed in commit bdbbb8527b ("ipv4: tcp: get rid of ugly unicast_sock")
This patch could very well surface old bugs, on layers not
taking care of sk->sk_kern_sock properly.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Prior patches in the series made sure tw_timer_handler()
can be fired after netns has been dismantled/freed.
We no longer have to scan a potentially big TCP ehash
table at netns dismantle.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Remove PDE_DATA() completely and replace it with pde_data().
[akpm@linux-foundation.org: fix naming clash in drivers/nubus/proc.c]
[akpm@linux-foundation.org: now fix it properly]
Link: https://lkml.kernel.org/r/20211124081956.87711-2-songmuchun@bytedance.com
Signed-off-by: Muchun Song <songmuchun@bytedance.com>
Acked-by: Christian Brauner <christian.brauner@ubuntu.com>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Alexey Gladkov <gladkov.alexey@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Replace kfree_skb() with kfree_skb_reason() in tcp_v4_rcv(). Following
drop reasons are added:
SKB_DROP_REASON_NO_SOCKET
SKB_DROP_REASON_PKT_TOO_SMALL
SKB_DROP_REASON_TCP_CSUM
SKB_DROP_REASON_TCP_FILTER
After this patch, 'kfree_skb' event will print message like this:
$ TASK-PID CPU# ||||| TIMESTAMP FUNCTION
$ | | | ||||| | |
<idle>-0 [000] ..s1. 36.113438: kfree_skb: skbaddr=(____ptrval____) protocol=2048 location=(____ptrval____) reason: NO_SOCKET
The reason of skb drop is printed too.
Signed-off-by: Menglong Dong <imagedong@tencent.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
The return value of BPF_CGROUP_RUN_PROG_INET{4,6}_POST_BIND() in
__inet_bind() is not handled properly. While the return value
is non-zero, it will set inet_saddr and inet_rcv_saddr to 0 and
exit:
err = BPF_CGROUP_RUN_PROG_INET4_POST_BIND(sk);
if (err) {
inet->inet_saddr = inet->inet_rcv_saddr = 0;
goto out_release_sock;
}
Let's take UDP for example and see what will happen. For UDP
socket, it will be added to 'udp_prot.h.udp_table->hash' and
'udp_prot.h.udp_table->hash2' after the sk->sk_prot->get_port()
called success. If 'inet->inet_rcv_saddr' is specified here,
then 'sk' will be in the 'hslot2' of 'hash2' that it don't belong
to (because inet_saddr is changed to 0), and UDP packet received
will not be passed to this sock. If 'inet->inet_rcv_saddr' is not
specified here, the sock will work fine, as it can receive packet
properly, which is wired, as the 'bind()' is already failed.
To undo the get_port() operation, introduce the 'put_port' field
for 'struct proto'. For TCP proto, it is inet_put_port(); For UDP
proto, it is udp_lib_unhash(); For icmp proto, it is
ping_unhash().
Therefore, after sys_bind() fail caused by
BPF_CGROUP_RUN_PROG_INET4_POST_BIND(), it will be unbinded, which
means that it can try to be binded to another port.
Signed-off-by: Menglong Dong <imagedong@tencent.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20220106132022.3470772-2-imagedong@tencent.com
tcp recvmsg() (or rx zerocopy) spends a fair amount of time
freeing skbs after their payload has been consumed.
A typical ~64KB GRO packet has to release ~45 page
references, eventually going to page allocator
for each of them.
Currently, this freeing is performed while socket lock
is held, meaning that there is a high chance that
BH handler has to queue incoming packets to tcp socket backlog.
This can cause additional latencies, because the user
thread has to process the backlog at release_sock() time,
and while doing so, additional frames can be added
by BH handler.
This patch adds logic to defer these frees after socket
lock is released, or directly from BH handler if possible.
Being able to free these skbs from BH handler helps a lot,
because this avoids the usual alloc/free assymetry,
when BH handler and user thread do not run on same cpu or
NUMA node.
One cpu can now be fully utilized for the kernel->user copy,
and another cpu is handling BH processing and skb/page
allocs/frees (assuming RFS is not forcing use of a single CPU)
Tested:
100Gbit NIC
Max throughput for one TCP_STREAM flow, over 10 runs
MTU : 1500
Before: 55 Gbit
After: 66 Gbit
MTU : 4096+(headers)
Before: 82 Gbit
After: 95 Gbit
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Instead of using a full netdev_features_t, we can use a single bit,
as sk_route_nocaps is only used to remove NETIF_F_GSO_MASK from
sk->sk_route_cap.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
If packet is going to be coalesced, sk_sndbuf/sk_rcvbuf values
are not used. Defer their access to the point we need them.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
RFC 5082 IP_MINTTL option is rarely used on hosts.
Add a static key to remove from TCP fast path useless code,
and potential cache line miss to fetch inet_sk(sk)->min_ttl
Note that once ip4_min_ttl static key has been enabled,
it stays enabled until next boot.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
No report yet from KCSAN, yet worth documenting the races.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Increase cache locality by moving rx_dst_ifindex next to sk->sk_rx_dst
This is part of an effort to reduce cache line misses in TCP fast path.
This removes one cache line miss in early demux.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Multiple VRFs are generally meant to be "separate" but right now md5
keys for the default VRF also affect connections inside VRFs if the IP
addresses happen to overlap.
So far the combination of TCP_MD5SIG_FLAG_IFINDEX with tcpm_ifindex == 0
was an error, accept this to mean "key only applies to default VRF".
This is what applications using VRFs for traffic separation want.
Signed-off-by: Leonard Crestez <cdleonard@gmail.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
With net.ipv4.tcp_l3mdev_accept=1 it is possible for a listen socket to
accept connection from the same client address in different VRFs. It is
also possible to set different MD5 keys for these clients which differ
only in the tcpm_l3index field.
This appears to work when distinguishing between different VRFs but not
between non-VRF and VRF connections. In particular:
* tcp_md5_do_lookup_exact will match a non-vrf key against a vrf key.
This means that adding a key with l3index != 0 after a key with l3index
== 0 will cause the earlier key to be deleted. Both keys can be present
if the non-vrf key is added later.
* _tcp_md5_do_lookup can match a non-vrf key before a vrf key. This
casues failures if the passwords differ.
Fix this by making tcp_md5_do_lookup_exact perform an actual exact
comparison on l3index and by making __tcp_md5_do_lookup perfer
vrf-bound keys above other considerations like prefixlen.
Fixes: dea53bb80e ("tcp: Add l3index to tcp_md5sig_key and md5 functions")
Signed-off-by: Leonard Crestez <cdleonard@gmail.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
This reverts the following patches :
- commit 2e05fcae83 ("tcp: fix compile error if !CONFIG_SYSCTL")
- commit 4f661542a4 ("tcp: fix zerocopy and notsent_lowat issues")
- commit 472c2e07ee ("tcp: add one skb cache for tx")
- commit 8b27dae5a2 ("tcp: add one skb cache for rx")
Having a cache of one skb (in each direction) per TCP socket is fragile,
since it can cause a significant increase of memory needs,
and not good enough for high speed flows anyway where more than one skb
is needed.
We want instead to add a generic infrastructure, with more flexible
per-cpu caches, for alien NUMA nodes.
Acked-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Andrii Nakryiko says:
====================
bpf-next 2021-07-30
We've added 64 non-merge commits during the last 15 day(s) which contain
a total of 83 files changed, 5027 insertions(+), 1808 deletions(-).
The main changes are:
1) BTF-guided binary data dumping libbpf API, from Alan.
2) Internal factoring out of libbpf CO-RE relocation logic, from Alexei.
3) Ambient BPF run context and cgroup storage cleanup, from Andrii.
4) Few small API additions for libbpf 1.0 effort, from Evgeniy and Hengqi.
5) bpf_program__attach_kprobe_opts() fixes in libbpf, from Jiri.
6) bpf_{get,set}sockopt() support in BPF iterators, from Martin.
7) BPF map pinning improvements in libbpf, from Martynas.
8) Improved module BTF support in libbpf and bpftool, from Quentin.
9) Bpftool cleanups and documentation improvements, from Quentin.
10) Libbpf improvements for supporting CO-RE on old kernels, from Shuyi.
11) Increased maximum cgroup storage size, from Stanislav.
12) Small fixes and improvements to BPF tests and samples, from various folks.
* https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (64 commits)
tools: bpftool: Complete metrics list in "bpftool prog profile" doc
tools: bpftool: Document and add bash completion for -L, -B options
selftests/bpf: Update bpftool's consistency script for checking options
tools: bpftool: Update and synchronise option list in doc and help msg
tools: bpftool: Complete and synchronise attach or map types
selftests/bpf: Check consistency between bpftool source, doc, completion
tools: bpftool: Slightly ease bash completion updates
unix_bpf: Fix a potential deadlock in unix_dgram_bpf_recvmsg()
libbpf: Add btf__load_vmlinux_btf/btf__load_module_btf
tools: bpftool: Support dumping split BTF by id
libbpf: Add split BTF support for btf__load_from_kernel_by_id()
tools: Replace btf__get_from_id() with btf__load_from_kernel_by_id()
tools: Free BTF objects at various locations
libbpf: Rename btf__get_from_id() as btf__load_from_kernel_by_id()
libbpf: Rename btf__load() as btf__load_into_kernel()
libbpf: Return non-null error on failures in libbpf_find_prog_btf_id()
bpf: Emit better log message if bpf_iter ctx arg btf_id == 0
tools/resolve_btfids: Emit warnings and patch zero id for missing symbols
bpf: Increase supported cgroup storage value size
libbpf: Fix race when pinning maps in parallel
...
====================
Link: https://lore.kernel.org/r/20210730225606.1897330-1-andrii@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
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: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Acked-by: Kuniyuki Iwashima <kuniyu@amazon.co.jp>
Acked-by: Yonghong 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: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Acked-by: Kuniyuki Iwashima <kuniyu@amazon.co.jp>
Acked-by: Yonghong 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: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Acked-by: Kuniyuki Iwashima <kuniyu@amazon.co.jp>
Acked-by: Yonghong 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: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Acked-by: Kuniyuki Iwashima <kuniyu@amazon.co.jp>
Acked-by: Yonghong 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: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Acked-by: Kuniyuki Iwashima <kuniyu@amazon.co.jp>
Acked-by: Yonghong 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: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Acked-by: Kuniyuki Iwashima <kuniyu@amazon.co.jp>
Acked-by: Yonghong 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: a8b690f98b ("tcp: Fix slowness in read /proc/net/tcp")
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Acked-by: Kuniyuki Iwashima <kuniyu@amazon.co.jp>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/bpf/20210701200541.1033917-1-kafai@fb.com
Multiple complaints have been raised from the TFO users on the internet
stating that the TFO blackhole logic is too aggressive and gets falsely
triggered too often.
(e.g. https://blog.apnic.net/2021/07/05/tcp-fast-open-not-so-fast/)
Considering that most middleboxes no longer drop TFO packets, we decide
to disable the blackhole logic by setting
/proc/sys/net/ipv4/tcp_fastopen_blackhole_timeout_set to 0 by default.
Fixes: cf1ef3f071 ("net/tcp_fastopen: Disable active side TFO in certain scenarios")
Signed-off-by: Wei Wang <weiwan@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
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: 563d34d057 ("tcp: dont drop MTU reduction indications")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David 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: Alexander Aring <aahringo@redhat.com>
Signed-off-by: David 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: Kuniyuki Iwashima <kuniyu@amazon.co.jp>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Acked-by: Martin 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: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David 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: Florian Westphal <fw@strlen.de>
Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: David 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: Cong Wang <cong.wang@bytedance.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210331023237.41094-11-xiyou.wangcong@gmail.com
Daniel Borkmann says:
====================
pull-request: bpf-next 2021-02-16
The following pull-request contains BPF updates for your *net-next* tree.
There's a small merge conflict between 7eeba1706e ("tcp: Add receive timestamp
support for receive zerocopy.") from net-next tree and 9cacf81f81 ("bpf: Remove
extra lock_sock for TCP_ZEROCOPY_RECEIVE") from bpf-next tree. Resolve as follows:
[...]
lock_sock(sk);
err = tcp_zerocopy_receive(sk, &zc, &tss);
err = BPF_CGROUP_RUN_PROG_GETSOCKOPT_KERN(sk, level, optname,
&zc, &len, err);
release_sock(sk);
[...]
We've added 116 non-merge commits during the last 27 day(s) which contain
a total of 156 files changed, 5662 insertions(+), 1489 deletions(-).
The main changes are:
1) Adds support of pointers to types with known size among global function
args to overcome the limit on max # of allowed args, from Dmitrii Banshchikov.
2) Add bpf_iter for task_vma which can be used to generate information similar
to /proc/pid/maps, from Song Liu.
3) Enable bpf_{g,s}etsockopt() from all sock_addr related program hooks. Allow
rewriting bind user ports from BPF side below the ip_unprivileged_port_start
range, both from Stanislav Fomichev.
4) Prevent recursion on fentry/fexit & sleepable programs and allow map-in-map
as well as per-cpu maps for the latter, from Alexei Starovoitov.
5) Add selftest script to run BPF CI locally. Also enable BPF ringbuffer
for sleepable programs, both from KP Singh.
6) Extend verifier to enable variable offset read/write access to the BPF
program stack, from Andrei Matei.
7) Improve tc & XDP MTU handling and add a new bpf_check_mtu() helper to
query device MTU from programs, from Jesper Dangaard Brouer.
8) Allow bpf_get_socket_cookie() helper also be called from [sleepable] BPF
tracing programs, from Florent Revest.
9) Extend x86 JIT to pad JMPs with NOPs for helping image to converge when
otherwise too many passes are required, from Gary Lin.
10) Verifier fixes on atomics with BPF_FETCH as well as function-by-function
verification both related to zero-extension handling, from Ilya Leoshkevich.
11) Better kernel build integration of resolve_btfids tool, from Jiri Olsa.
12) Batch of AF_XDP selftest cleanups and small performance improvement
for libbpf's xsk map redirect for newer kernels, from Björn Töpel.
13) Follow-up BPF doc and verifier improvements around atomics with
BPF_FETCH, from Brendan Jackman.
14) Permit zero-sized data sections e.g. if ELF .rodata section contains
read-only data from local variables, from Yonghong Song.
15) veth driver skb bulk-allocation for ndo_xdp_xmit, from Lorenzo Bianconi.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch avoids the indirect call for the common case:
ip6_dst_check and ipv4_dst_check
Signed-off-by: Brian Vazquez <brianvv@google.com>
Signed-off-by: Jakub 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: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Martin 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 01770a1661 ("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: 01770a1661 ("tcp: fix race condition when creating child sockets from syncookies")
CC: Ricardo Dias <rdias@singlestore.com>
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.co.jp>
Reviewed-by: Benjamin Herrenschmidt <benh@amazon.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20210118055920.82516-1-kuniyu@amazon.co.jp
Signed-off-by: Jakub 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: 4f693b55c3 ("tcp: implement coalescing on backlog queue")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Bisected-by: Juerg Haefliger <juergh@canonical.com>
Tested-by: Juerg Haefliger <juergh@canonical.com>
Reported-by: Heiner 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.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Eric Dumazet
Jakub Kicinski
Dmitry Safonov
Menglong Dong
Linus Torvalds
Muchun Song
David S. Miller
Leonard Crestez
Martin KaFai Lau
Wei Wang
Alexander Aring
Kuniyuki Iwashima
Florian Westphal
Cong Wang
Brian Vazquez
Stanislav Fomichev