ip6mr does not have rtnetlink interface for MFC unlike ipmr,
which uses dev_get_by_index_rcu() to set struct mfcctl.mfcc_parent.
ip6mr_mfc_add() and ip6mr_mfc_delete() are called under RTNL
from ip6_mroute_setsockopt() only.
There are no RTNL dependant, but ip6_mroute_setsockopt() reuses
RTNL just for mrt->mfc_hash and mrt->mfc_cache_list.
Let's replace RTNL with a new per-netns mutex.
Later, ip6mr_notifier_ops and ipmr_seq will be moved under
CONFIG_IPV6_MROUTE.
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20260604224712.3209821-15-kuniyu@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
fl_size, fl_ht and ip6_fl_lock in net/ipv6/ip6_flowlabel.c are
file scope and shared across netns. mem_check() reads fl_size to
decide whether to deny non-CAP_NET_ADMIN callers. capable() runs
against init_user_ns, so an unprivileged user in any non-init
userns can push fl_size past FL_MAX_SIZE - FL_MAX_SIZE / 4 and
starve every other unprivileged userns on the host.
Add struct netns_ipv6::flowlabel_count, bumped and decremented
next to fl_size in fl_intern, ip6_fl_gc and ip6_fl_purge. The new
field fills the existing 4-byte hole after ipmr_seq, so struct
netns_ipv6 stays the same size on 64-bit builds.
Bump FL_MAX_SIZE from 4096 to 8192. It has been 4096 since the
file was added. Machines and connection counts have grown.
mem_check() folds an extra per-netns ceiling into the existing
non-CAP_NET_ADMIN conditional. The ceiling is half of the total
budget that unprivileged callers have ever been able to use, i.e.
(FL_MAX_SIZE - FL_MAX_SIZE / 4) / 2 = 3072 entries. With
FL_MAX_SIZE doubled, this preserves the original per-user reach
of 3K (what an unprivileged caller could already obtain before
this change), while forcing an attacker to spread allocations
across at least two netns to exhaust the global non-CAP_NET_ADMIN
budget.
CAP_NET_ADMIN against init_user_ns still bypasses both caps.
The previous patch took ip6_fl_lock across mem_check and
fl_intern, so the new flowlabel_count read in mem_check and the
new flowlabel_count++ in fl_intern run under the same critical
section. flowlabel_count is therefore plain int, like fl_size.
Fixes: 1da177e4c3 ("Linux-2.6.12-rc2")
Suggested-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Cc: stable@vger.kernel.org # v5.15+
Signed-off-by: Maoyi Xie <maoyi.xie@ntu.edu.sg>
Link: https://patch.msgid.link/20260506082416.2259567-3-maoyixie.tju@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
The RCU-protected codepaths (mpls_forward, mpls_dump_routes) can have
an inconsistent view of platform_labels vs platform_label in case of a
concurrent resize (resize_platform_label_table, under
platform_mutex). This can lead to OOB accesses.
This patch adds a seqcount, so that we get a consistent snapshot.
Note that mpls_label_ok is also susceptible to this, so the check
against RTA_DST in rtm_to_route_config, done outside platform_mutex,
is not sufficient. This value gets passed to mpls_label_ok once more
in both mpls_route_add and mpls_route_del, so there is no issue, but
that additional check must not be removed.
Reported-by: Yuan Tan <tanyuan98@outlook.com>
Reported-by: Yifan Wu <yifanwucs@gmail.com>
Reported-by: Juefei Pu <tomapufckgml@gmail.com>
Reported-by: Xin Liu <bird@lzu.edu.cn>
Fixes: 7720c01f3f ("mpls: Add a sysctl to control the size of the mpls label table")
Fixes: dde1b38e87 ("mpls: Convert mpls_dump_routes() to RCU.")
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Link: https://patch.msgid.link/cd8fca15e3eb7e212b094064cd83652e20fd9d31.1774284088.git.sd@queasysnail.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Steffen Klassert says:
====================
pull request (net): ipsec 2026-03-23
1) Add missing extack for XFRMA_SA_PCPU in add_acquire and allocspi.
From Sabrina Dubroca.
2) Fix the condition on x->pcpu_num in xfrm_sa_len by using the
proper check. From Sabrina Dubroca.
3) Call xdo_dev_state_delete during state update to properly cleanup
the xdo device state. From Sabrina Dubroca.
4) Fix a potential skb leak in espintcp when async crypto is used.
From Sabrina Dubroca.
5) Validate inner IPv4 header length in IPTFS payload to avoid
parsing malformed packets. From Roshan Kumar.
6) Fix skb_put() panic on non-linear skb during IPTFS reassembly.
From Fernando Fernandez Mancera.
7) Silence various sparse warnings related to RCU, state, and policy
handling. From Sabrina Dubroca.
8) Fix work re-schedule race after cancel in xfrm_nat_keepalive_net_fini().
From Hyunwoo Kim.
9) Prevent policy_hthresh.work from racing with netns teardown by using
a proper cleanup mechanism. From Minwoo Ra.
10) Validate that the family of the source and destination addresses match
in pfkey_send_migrate(). From Eric Dumazet.
11) Only publish mode_data after the clone is setup in the IPTFS receive path.
This prevents leaving x->mode_data pointing at freed memory on error.
From Paul Moses.
Please pull or let me know if there are problems.
ipsec-2026-03-23
* tag 'ipsec-2026-03-23' of git://git.kernel.org/pub/scm/linux/kernel/git/klassert/ipsec:
xfrm: iptfs: only publish mode_data after clone setup
af_key: validate families in pfkey_send_migrate()
xfrm: prevent policy_hthresh.work from racing with netns teardown
xfrm: Fix work re-schedule after cancel in xfrm_nat_keepalive_net_fini()
xfrm: avoid RCU warnings around the per-netns netlink socket
xfrm: add rcu_access_pointer to silence sparse warning for xfrm_input_afinfo
xfrm: policy: silence sparse warning in xfrm_policy_unregister_afinfo
xfrm: policy: fix sparse warnings in xfrm_policy_{init,fini}
xfrm: state: silence sparse warnings during netns exit
xfrm: remove rcu/state_hold from xfrm_state_lookup_spi_proto
xfrm: state: add xfrm_state_deref_prot to state_by* walk under lock
xfrm: state: fix sparse warnings around XFRM_STATE_INSERT
xfrm: state: fix sparse warnings in xfrm_state_init
xfrm: state: fix sparse warnings on xfrm_state_hold_rcu
xfrm: iptfs: fix skb_put() panic on non-linear skb during reassembly
xfrm: iptfs: validate inner IPv4 header length in IPTFS payload
esp: fix skb leak with espintcp and async crypto
xfrm: call xdo_dev_state_delete during state update
xfrm: fix the condition on x->pcpu_num in xfrm_sa_len
xfrm: add missing extack for XFRMA_SA_PCPU in add_acquire and allocspi
====================
Link: https://patch.msgid.link/20260323083440.2741292-1-steffen.klassert@secunet.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
When no H2G transport is loaded, vsock currently routes all CIDs to the
G2H transport (commit 65b422d9b6 ("vsock: forward all packets to the
host when no H2G is registered"). Extend that existing behavior: when
an H2G transport is loaded but does not claim a given CID, the
connection falls back to G2H in the same way.
This matters in environments like Nitro Enclaves, where an instance may
run nested VMs via vhost-vsock (H2G) while also needing to reach sibling
enclaves at higher CIDs through virtio-vsock-pci (G2H). With the old
code, any CID > 2 was unconditionally routed to H2G when vhost was
loaded, making those enclaves unreachable without setting
VMADDR_FLAG_TO_HOST explicitly on every connect.
Requiring every application to set VMADDR_FLAG_TO_HOST creates friction:
tools like socat, iperf, and others would all need to learn about it.
The flag was introduced 6 years ago and I am still not aware of any tool
that supports it. Even if there was support, it would be cumbersome to
use. The most natural experience is a single CID address space where H2G
only wins for CIDs it actually owns, and everything else falls through to
G2H, extending the behavior that already exists when H2G is absent.
To give user space at least a hint that the kernel applied this logic,
automatically set the VMADDR_FLAG_TO_HOST on the remote address so it
can determine the path taken via getpeername().
Add a per-network namespace sysctl net.vsock.g2h_fallback (default 1).
At 0 it forces strict routing: H2G always wins for CID > VMADDR_CID_HOST,
or ENODEV if H2G is not loaded.
Signed-off-by: Alexander Graf <graf@amazon.com>
Tested-by: syzbot@syzkaller.appspotmail.com
Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
Link: https://patch.msgid.link/20260304230027.59857-1-graf@amazon.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
net->xfrm.nlsk is used in 2 types of contexts:
- fully under RCU, with rcu_read_lock + rcu_dereference and a NULL check
- in the netlink handlers, with requests coming from a userspace socket
In the 2nd case, net->xfrm.nlsk is guaranteed to stay non-NULL and the
object is alive, since we can't enter the netns destruction path while
the user socket holds a reference on the netns.
After adding the __rcu annotation to netns_xfrm.nlsk (which silences
sparse warnings in the RCU users and __net_init code), we need to tell
sparse that the 2nd case is safe. Add a helper for that.
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
With the current port selection algorithm, ports after a reserved port
range or long time used port are used more often than others [1]. This
causes an uneven port usage distribution. This combines with cloud
environments blocking connections between the application server and the
database server if there was a previous connection with the same source
port, leading to connectivity problems between applications on cloud
environments.
The real issue here is that these firewalls cannot cope with
standards-compliant port reuse. This is a workaround for such situations
and an improvement on the distribution of ports selected.
The proposed solution is to implement a variant of RFC 6056 Algorithm 5.
The step size is selected randomly on every connect() call ensuring it
is a coprime with respect to the size of the range of ports we want to
scan. This way, we can ensure that all ports within the range are
scanned before returning an error. To enable this algorithm, the user
must configure the new sysctl option "net.ipv4.ip_local_port_step_width".
In addition, on graphs generated we can observe that the distribution of
source ports is more even with the proposed approach. [2]
[1] https://0xffsoftware.com/port_graph_current_alg.html
[2] https://0xffsoftware.com/port_graph_random_step_alg.html
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Fernando Fernandez Mancera <fmancera@suse.de>
Link: https://patch.msgid.link/20260309023946.5473-2-fmancera@suse.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Commit 18fd64d254 ("netns-ipv4: reorganize netns_ipv4 fast path
variables") missed that __tcp_select_window() is reading
net->ipv4.sysctl_tcp_shrink_window.
Move this field to netns_ipv4_read_txrx group, as __tcp_select_window()
is used both in tx and rx paths.
Saves a potential cache line miss.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20260307092214.2433548-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
We will no longer hold RTNL for ipmr_rtm_route() to modify the
MFC hash table.
Only __dev_get_by_index() in rtm_to_ipmr_mfcc() is the RTNL
dependant, otherwise, we just need protection for mrt->mfc_hash
and mrt->mfc_cache_list.
Let's add a new mutex for ipmr_mfc_add(), ipmr_mfc_delete(),
and mroute_clean_tables() (setsockopt(MRT_FLUSH or MRT_DONE)).
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20260228221800.1082070-15-kuniyu@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
We will no longer hold RTNL for ipmr_mfc_add() and ipmr_mfc_delete().
MFC entry can be loosely connected with VIF by its index for
mrt->vif_table[] (stored in mfc_parent), but the two tables are
not synchronised. i.e. Even if VIF 1 is removed, MFC for VIF 1
is not automatically removed.
The only field that the MFC/VIF interfaces share is
net->ipv[46].ipmr_seq, which is protected by RTNL.
Adding a new mutex for both just to protect a single field is overkill.
Let's convert the field to atomic_t.
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20260228221800.1082070-14-kuniyu@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Two administrator processes may race when setting child_ns_mode as one
process sets child_ns_mode to "local" and then creates a namespace, but
another process changes child_ns_mode to "global" between the write and
the namespace creation. The first process ends up with a namespace in
"global" mode instead of "local". While this can be detected after the
fact by reading ns_mode and retrying, it is fragile and error-prone.
Make child_ns_mode write-once so that a namespace manager can set it
once and be sure it won't change. Writing a different value after the
first write returns -EBUSY. This applies to all namespaces, including
init_net, where an init process can write "local" to lock all future
namespaces into local mode.
Fixes: eafb64f40c ("vsock: add netns to vsock core")
Suggested-by: Daan De Meyer <daan.j.demeyer@gmail.com>
Suggested-by: Stefano Garzarella <sgarzare@redhat.com>
Co-developed-by: Stefano Garzarella <sgarzare@redhat.com>
Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
Signed-off-by: Bobby Eshleman <bobbyeshleman@meta.com>
Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
Link: https://patch.msgid.link/20260223-vsock-ns-write-once-v3-2-c0cde6959923@meta.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
icmp_global_credit was meant to be changed ~1000 times per second,
but if an admin sets net.ipv4.icmp_msgs_per_sec to a very high value,
icmp_global_credit changes can inflict false sharing to surrounding
fields that are read mostly.
Move icmp_global_credit and icmp_global_stamp to a separate
cacheline aligned group.
Fixes: b056b4cd91 ("icmp: move icmp_global.credit and icmp_global.stamp to per netns storage")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20260216142832.3834174-3-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Add netns logic to vsock core. Additionally, modify transport hook
prototypes to be used by later transport-specific patches (e.g.,
*_seqpacket_allow()).
Namespaces are supported primarily by changing socket lookup functions
(e.g., vsock_find_connected_socket()) to take into account the socket
namespace and the namespace mode before considering a candidate socket a
"match".
This patch also introduces the sysctl /proc/sys/net/vsock/ns_mode to
report the mode and /proc/sys/net/vsock/child_ns_mode to set the mode
for new namespaces.
Add netns functionality (initialization, passing to transports, procfs,
etc...) to the af_vsock socket layer. Later patches that add netns
support to transports depend on this patch.
This patch changes the allocation of random ports for connectible vsocks
in order to avoid leaking the random port range starting point to other
namespaces.
dgram_allow(), stream_allow(), and seqpacket_allow() callbacks are
modified to take a vsk in order to perform logic on namespace modes. In
future patches, the net will also be used for socket
lookups in these functions.
Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
Signed-off-by: Bobby Eshleman <bobbyeshleman@meta.com>
Link: https://patch.msgid.link/20260121-vsock-vmtest-v16-1-2859a7512097@meta.com
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Group together following struct netns_sysctl_ipv6 fields:
- flowlabel_consistency
- auto_flowlabels
- flowlabel_state_ranges
After this patch, ip6_make_flowlabel() uses a single cache line to fetch
auto_flowlabels and flowlabel_state_ranges (instead of two before the patch).
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20260115094141.3124990-2-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
The introduction of IPPROTO_SMC enables eBPF programs to determine
whether to use SMC based on the context of socket creation, such as
network namespaces, PID and comm name, etc.
As a subsequent enhancement, to introduce a new generic hook that
allows decisions on whether to use SMC or not at runtime, including
but not limited to local/remote IP address or ports.
User can write their own implememtion via bpf_struct_ops now to choose
whether to use SMC or not before TCP 3rd handshake to be comleted.
Signed-off-by: D. Wythe <alibuda@linux.alibaba.com>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Reviewed-by: Dust Li <dust.li@linux.alibaba.com>
Link: https://patch.msgid.link/20251107035632.115950-3-alibuda@linux.alibaba.com
TCP SACK compression has been added in 2018 in commit
5d9f4262b7 ("tcp: add SACK compression").
It is working great for WAN flows (with large RTT).
Wifi in particular gets a significant boost _when_ ACK are suppressed.
Add a new sysctl so that we can tune the very conservative 5 % value
that has been used so far in this formula, so that small RTT flows
can benefit from this feature.
delay = min ( 5 % of RTT, 1 ms)
This patch adds new tcp_comp_sack_rtt_percent sysctl
to ease experiments and tuning.
Given that we cap the delay to 1ms (tcp_comp_sack_delay_ns sysctl),
set the default value to 33 %.
Quoting Neal Cardwell ( https://lore.kernel.org/netdev/CADVnQymZ1tFnEA1Q=vtECs0=Db7zHQ8=+WCQtnhHFVbEOzjVnQ@mail.gmail.com/ )
The rationale for 33% is basically to try to facilitate pipelining,
where there are always at least 3 ACKs and 3 GSO/TSO skbs per SRTT, so
that the path can maintain a budget for 3 full-sized GSO/TSO skbs "in
flight" at all times:
+ 1 skb in the qdisc waiting to be sent by the NIC next
+ 1 skb being sent by the NIC (being serialized by the NIC out onto the wire)
+ 1 skb being received and aggregated by the receiver machine's
aggregation mechanism (some combination of LRO, GRO, and sack
compression)
Note that this is basically the same magic number (3) and the same
rationales as:
(a) tcp_tso_should_defer() ensuring that we defer sending data for no
longer than cwnd/tcp_tso_win_divisor (where tcp_tso_win_divisor = 3),
and
(b) bbr_quantization_budget() ensuring that cwnd is at least 3 GSO/TSO
skbs to maintain pipelining and full throughput at low RTTs
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Neal Cardwell <ncardwell@google.com>
Link: https://patch.msgid.link/20251106115236.3450026-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
