UDP TX packets destructor is sock_wfree().
It suffers from a cache line bouncing in sock_def_write_space_wfree().
Instead of reading sk->sk_wmem_alloc after we just did an atomic RMW
on it, use __refcount_sub_and_test() to get the old value for free,
and pass the new value to sock_def_write_space_wfree().
Add __sock_writeable() helper.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20251017133712.2842665-1-edumazet@google.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Martin KaFai Lau says:
====================
pull-request: bpf-next 2025-10-16
We've added 6 non-merge commits during the last 1 day(s) which contain
a total of 18 files changed, 577 insertions(+), 38 deletions(-).
The main changes are:
1) Bypass the global per-protocol memory accounting either by setting
a netns sysctl or using bpf_setsockopt in a bpf program,
from Kuniyuki Iwashima.
* tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next:
selftests/bpf: Add test for sk->sk_bypass_prot_mem.
bpf: Introduce SK_BPF_BYPASS_PROT_MEM.
bpf: Support bpf_setsockopt() for BPF_CGROUP_INET_SOCK_CREATE.
net: Introduce net.core.bypass_prot_mem sysctl.
net: Allow opt-out from global protocol memory accounting.
tcp: Save lock_sock() for memcg in inet_csk_accept().
====================
Link: https://patch.msgid.link/20251016204539.773707-1-martin.lau@linux.dev
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Since ehash lookups are lockless, if one CPU performs a lookup while
another concurrently deletes and inserts (removing reqsk and inserting sk),
the lookup may fail to find the socket, an RST may be sent.
The call trace map is drawn as follows:
CPU 0 CPU 1
----- -----
inet_ehash_insert()
spin_lock()
sk_nulls_del_node_init_rcu(osk)
__inet_lookup_established()
(lookup failed)
__sk_nulls_add_node_rcu(sk, list)
spin_unlock()
As both deletion and insertion operate on the same ehash chain, this patch
introduces a new sk_nulls_replace_node_init_rcu() helper functions to
implement atomic replacement.
Fixes: 5e0724d027 ("tcp/dccp: fix hashdance race for passive sessions")
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Reviewed-by: Jiayuan Chen <jiayuan.chen@linux.dev>
Signed-off-by: Xuanqiang Luo <luoxuanqiang@kylinos.cn>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20251015020236.431822-3-xuanqiang.luo@linux.dev
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Some protocols (e.g., TCP, UDP) implement memory accounting for socket
buffers and charge memory to per-protocol global counters pointed to by
sk->sk_proto->memory_allocated.
Sometimes, system processes do not want that limitation. For a similar
purpose, there is SO_RESERVE_MEM for sockets under memcg.
Also, by opting out of the per-protocol accounting, sockets under memcg
can avoid paying costs for two orthogonal memory accounting mechanisms.
A microbenchmark result is in the subsequent bpf patch.
Let's allow opt-out from the per-protocol memory accounting if
sk->sk_bypass_prot_mem is true.
sk->sk_bypass_prot_mem and sk->sk_prot are placed in the same cache
line, and sk_has_account() always fetches sk->sk_prot before accessing
sk->sk_bypass_prot_mem, so there is no extra cache miss for this patch.
The following patches will set sk->sk_bypass_prot_mem to true, and
then, the per-protocol memory accounting will be skipped.
Note that this does NOT disable memcg, but rather the per-protocol one.
Another option not to use the hole in struct sock_common is create
sk_prot variants like tcp_prot_bypass, but this would complicate
SOCKMAP logic, tcp_bpf_prots etc.
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Reviewed-by: Shakeel Butt <shakeel.butt@linux.dev>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Acked-by: Roman Gushchin <roman.gushchin@linux.dev>
Link: https://patch.msgid.link/20251014235604.3057003-3-kuniyu@google.com
This is a followup of commit 726e9e8b94 ("tcp: refine
skb->ooo_okay setting") and of prior commit in this series
("net: control skb->ooo_okay from skb_set_owner_w()")
skb->ooo_okay might never be set for bulk flows that always
have at least one skb in a qdisc queue of NIC queue,
especially if TX completion is delayed because of a stressed cpu.
The so-called "strange attractors" has caused many performance
issues (see for instance 9b462d02d6 ("tcp: TCP Small Queues
and strange attractors")), we need to do better.
We have tried very hard to avoid reorders because TCP was
not dealing with them nicely a decade ago.
Use the new net.core.txq_reselection_ms sysctl to let
flows follow XPS and select a more efficient queue.
After this patch, we no longer have to make sure threads
are pinned to cpus, they now can be migrated without
adding too much spinlock/qdisc/TX completion pressure anymore.
TX completion part was problematic, because it added false sharing
on various socket fields, but also added false sharing and spinlock
contention in mm layers. Calling skb_orphan() from ndo_start_xmit()
is not an option unfortunately.
Note for later:
1) move sk->sk_tx_queue_mapping closer
to sk_tx_queue_mapping_jiffies for better cache locality.
2) Study if 9b462d02d6 ("tcp: TCP Small Queues
and strange attractors") could be revised.
Tested:
Used a host with 32 TX queues, shared by groups of 8 cores.
XPS setup :
echo ff >/sys/class/net/eth1/queue/tx-0/xps_cpus
echo ff00 >/sys/class/net/eth1/queue/tx-1/xps_cpus
echo ff0000 >/sys/class/net/eth1/queue/tx-2/xps_cpus
echo ff000000 >/sys/class/net/eth1/queue/tx-3/xps_cpus
echo ff,00000000 >/sys/class/net/eth1/queue/tx-4/xps_cpus
echo ff00,00000000 >/sys/class/net/eth1/queue/tx-5/xps_cpus
echo ff0000,00000000 >/sys/class/net/eth1/queue/tx-6/xps_cpus
echo ff000000,00000000 >/sys/class/net/eth1/queue/tx-7/xps_cpus
...
Launched a tcp_stream with 15 threads and 1000 flows, initially affined to core 0-15
taskset -c 0-15 tcp_stream -T15 -F1000 -l1000 -c -H target_host
Checked that only queues 0 and 1 are used as instructed by XPS :
tc -s qdisc show dev eth1|grep backlog|grep -v "backlog 0b 0p"
backlog 123489410b 1890p
backlog 69809026b 1064p
backlog 52401054b 805p
Then force each thread to run on cpu 1,9,17,25,33,41,49,57,65,73,81,89,97,105,113,121
C=1;PID=`pidof tcp_stream`;for P in `ls /proc/$PID/task`; do taskset -pc $C $P; C=$(($C + 8));done
Set txq_reselection_ms to 1000
echo 1000 > /proc/sys/net/core/txq_reselection_ms
Check that the flows have migrated nicely:
tc -s qdisc show dev eth1|grep backlog|grep -v "backlog 0b 0p"
backlog 130508314b 1916p
backlog 8584380b 126p
backlog 8584380b 126p
backlog 8379990b 123p
backlog 8584380b 126p
backlog 8487484b 125p
backlog 8584380b 126p
backlog 8448120b 124p
backlog 8584380b 126p
backlog 8720640b 128p
backlog 8856900b 130p
backlog 8584380b 126p
backlog 8652510b 127p
backlog 8448120b 124p
backlog 8516250b 125p
backlog 7834950b 115p
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20251013152234.842065-5-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Today, once an inet_bind_bucket enters a state where fastreuse >= 0 or
fastreuseport >= 0 after a socket is explicitly bound to a port, it remains
in that state until all sockets are removed and the bucket is destroyed.
In this state, the bucket is skipped during ephemeral port selection in
connect(). For applications using a reduced ephemeral port
range (IP_LOCAL_PORT_RANGE socket option), this can cause faster port
exhaustion since blocked buckets are excluded from reuse.
The reason the bucket state isn't updated on port release is unclear.
Possibly a performance trade-off to avoid scanning bucket owners, or just
an oversight.
Fix it by recalculating the bucket state when a socket releases a port. To
limit overhead, each inet_bind2_bucket stores its own (fastreuse,
fastreuseport) state. On port release, only the relevant port-addr bucket
is scanned, and the overall state is derived from these.
Signed-off-by: Jakub Sitnicki <jakub@cloudflare.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20250917-update-bind-bucket-state-on-unhash-v5-1-57168b661b47@cloudflare.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
sk->sk_sndbuf is read-mostly in tx path, so move it from
sock_write_tx group to more appropriate sock_read_tx.
sk->sk_err_soft was not identified previously, but
is used from tcp_ack().
Move it to sock_write_tx group for better cache locality.
Also change tcp_ack() to clear sk->sk_err_soft only if needed.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20250919204856.2977245-3-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Cross-merge networking fixes after downstream PR (net-6.17-rc7).
No conflicts.
Adjacent changes:
drivers/net/ethernet/mellanox/mlx5/core/en/fs.h
9536fbe10c ("net/mlx5e: Add PSP steering in local NIC RX")
7601a0a462 ("net/mlx5e: Add a miss level for ipsec crypto offload")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Move definition of sk_validate_xmit_skb() from net/core/sock.c to
net/core/dev.c.
This change is in preparation of the next patch, where
sk_validate_xmit_skb() will need to cast sk to a tcp_timewait_sock *,
and access member fields. Including linux/tcp.h from linux/sock.h
creates a circular dependency, and dev.c is the only current call site
of this function.
Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Daniel Zahka <daniel.zahka@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20250917000954.859376-7-daniel.zahka@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Hosts under DOS attack can suffer from false sharing
in enqueue_to_backlog() : atomic_inc(&sd->dropped).
This is because sd->dropped can be touched from many cpus,
possibly residing on different NUMA nodes.
Generalize the sk_drop_counters infrastucture
added in commit c51613fa27 ("net: add sk->sk_drop_counters")
and use it to replace softnet_data.dropped
with NUMA friendly softnet_data.drop_counters.
This adds 64 bytes per cpu, maybe more in the future
if we increase the number of counters (currently 2)
per 'struct numa_drop_counters'.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20250909121942.1202585-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
TCP tracks the number of orphaned (SOCK_DEAD but not yet destructed)
sockets in tcp_orphan_count.
In some code that was shared with DCCP, tcp_orphan_count is referenced
via sk->sk_prot->orphan_count.
Let's reference tcp_orphan_count directly.
inet_csk_prepare_for_destroy_sock() is moved to inet_connection_sock.c
due to header dependency.
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Reviewed-by: Jason Xing <kerneljasonxing@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20250829215641.711664-1-kuniyu@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
We will store a flag in the lowest bit of sk->sk_memcg.
Then, directly dereferencing sk->sk_memcg will be illegal, and we
do not want to allow touching the raw sk->sk_memcg in many places.
Let's introduce mem_cgroup_from_sk().
Other places accessing the raw sk->sk_memcg will be converted later.
Note that we cannot define the helper as an inline function in
memcontrol.h as we cannot access any fields of struct sock there
due to circular dependency, so it is placed in sock.h.
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Acked-by: Roman Gushchin <roman.gushchin@linux.dev>
Acked-by: Shakeel Butt <shakeel.butt@linux.dev>
Link: https://patch.msgid.link/20250815201712.1745332-7-kuniyu@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Followup of commit 285975dd67 ("net: annotate data-races around
sk->sk_{rcv|snd}timeo").
Remove lock_sock()/release_sock() from ksmbd_tcp_rcv_timeout()
and add READ_ONCE()/WRITE_ONCE() where it is needed.
Also SO_RCVTIMEO_OLD and SO_RCVTIMEO_NEW can call sock_set_timeout()
without holding the socket lock.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20250620155536.335520-3-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Followup of commit 285975dd67 ("net: annotate data-races around
sk->sk_{rcv|snd}timeo").
Remove lock_sock()/release_sock() from sock_set_sndtimeo(),
and add READ_ONCE()/WRITE_ONCE() where it is needed.
Also SO_SNDTIMEO_OLD and SO_SNDTIMEO_NEW can call sock_set_timeout()
without holding the socket lock.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20250620155536.335520-2-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Difference between sock_i_uid() and sk_uid() is that
after sock_orphan(), sock_i_uid() returns GLOBAL_ROOT_UID
while sk_uid() returns the last cached sk->sk_uid value.
None of sock_i_uid() callers care about this.
Use sk_uid() which is much faster and inlined.
Note that diag/dump users are calling sock_i_ino() and
can not see the full benefit yet.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Lorenzo Colitti <lorenzo@google.com>
Reviewed-by: Maciej Żenczykowski <maze@google.com>
Link: https://patch.msgid.link/20250620133001.4090592-3-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
sk->sk_prot->sock_is_readable is a valid function pointer when sk resides
in a sockmap. After the last sk_psock_put() (which usually happens when
socket is removed from sockmap), sk->sk_prot gets restored and
sk->sk_prot->sock_is_readable becomes NULL.
This makes sk_is_readable() racy, if the value of sk->sk_prot is reloaded
after the initial check. Which in turn may lead to a null pointer
dereference.
Ensure the function pointer does not turn NULL after the check.
Fixes: 8934ce2fd0 ("bpf: sockmap redirect ingress support")
Suggested-by: Jakub Sitnicki <jakub@cloudflare.com>
Signed-off-by: Michal Luczaj <mhal@rbox.co>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/20250609-skisreadable-toctou-v1-1-d0dfb2d62c37@rbox.co
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
As long as recvmsg() or recvmmsg() is used with cmsg, it is not
possible to avoid receiving file descriptors via SCM_RIGHTS.
This behaviour has occasionally been flagged as problematic, as
it can be (ab)used to trigger DoS during close(), for example, by
passing a FUSE-controlled fd or a hung NFS fd.
For instance, as noted on the uAPI Group page [0], an untrusted peer
could send a file descriptor pointing to a hung NFS mount and then
close it. Once the receiver calls recvmsg() with msg_control, the
descriptor is automatically installed, and then the responsibility
for the final close() now falls on the receiver, which may result
in blocking the process for a long time.
Regarding this, systemd calls cmsg_close_all() [1] after each
recvmsg() to close() unwanted file descriptors sent via SCM_RIGHTS.
However, this cannot work around the issue at all, because the final
fput() may still occur on the receiver's side once sendmsg() with
SCM_RIGHTS succeeds. Also, even filtering by LSM at recvmsg() does
not work for the same reason.
Thus, we need a better way to refuse SCM_RIGHTS at sendmsg().
Let's introduce SO_PASSRIGHTS to disable SCM_RIGHTS.
Note that this option is enabled by default for backward
compatibility.
Link: https://uapi-group.org/kernel-features/#disabling-reception-of-scm_rights-for-af_unix-sockets #[0]
Link: https://github.com/systemd/systemd/blob/v257.5/src/basic/fd-util.c#L612-L628 #[1]
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
As explained in the next patch, SO_PASSRIGHTS would have a problem
if we assigned a corresponding bit to socket->flags, so it must be
managed in struct sock.
Mixing socket->flags and sk->sk_flags for similar options will look
confusing, and sk->sk_flags does not have enough space on 32bit system.
Also, as mentioned in commit 16e5726269 ("af_unix: dont send
SCM_CREDENTIALS by default"), SOCK_PASSCRED and SOCK_PASSPID handling
is known to be slow, and managing the flags in struct socket cannot
avoid that for embryo sockets.
Let's move SOCK_PASS{CRED,PIDFD,SEC} to struct sock.
While at it, other SOCK_XXX flags in net.h are grouped as enum.
Note that assign_bit() was atomic, so the writer side is moved down
after lock_sock() in setsockopt(), but the bit is only read once
in sendmsg() and recvmsg(), so lock_sock() is not needed there.
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
SCM_CREDENTIALS and SCM_SECURITY can be recv()ed by calling
scm_recv() or scm_recv_unix(), and SCM_PIDFD is only used by
scm_recv_unix().
scm_recv() is called from AF_NETLINK and AF_BLUETOOTH.
scm_recv_unix() is literally called from AF_UNIX.
Let's restrict SO_PASSCRED and SO_PASSSEC to such sockets and
SO_PASSPIDFD to AF_UNIX only.
Later, SOCK_PASS{CRED,PIDFD,SEC} will be moved to struct sock
and united with another field.
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Checking the SOCK_WIFI_STATUS flag bit in sk_flags may give wrong results
since sk_flags are part of a union and the union is used otherwise. Add
sk_requests_wifi_status() which checks if sk is non-NULL, sk is a full
socket (so flags are valid) and checks the flag bit.
Fixes: 76a853f86c ("wifi: free SKBTX_WIFI_STATUS skb tx_flags flag")
Suggested-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Bert Karwatzki <spasswolf@web.de>
Reviewed-by: Jason Xing <kerneljasonxing@gmail.com>
Link: https://patch.msgid.link/20250520223430.6875-1-spasswolf@web.de
[edit commit message, fix indentation]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Augment dmabuf binding to be able to handle TX. Additional to all the RX
binding, we also create tx_vec needed for the TX path.
Provide API for sendmsg to be able to send dmabufs bound to this device:
- Provide a new dmabuf_tx_cmsg which includes the dmabuf to send from.
- MSG_ZEROCOPY with SCM_DEVMEM_DMABUF cmsg indicates send from dma-buf.
Devmem is uncopyable, so piggyback off the existing MSG_ZEROCOPY
implementation, while disabling instances where MSG_ZEROCOPY falls back
to copying.
We additionally pipe the binding down to the new
zerocopy_fill_skb_from_devmem which fills a TX skb with net_iov netmems
instead of the traditional page netmems.
We also special case skb_frag_dma_map to return the dma-address of these
dmabuf net_iovs instead of attempting to map pages.
The TX path may release the dmabuf in a context where we cannot wait.
This happens when the user unbinds a TX dmabuf while there are still
references to its netmems in the TX path. In that case, the netmems will
be put_netmem'd from a context where we can't unmap the dmabuf, Resolve
this by making __net_devmem_dmabuf_binding_free schedule_work'd.
Based on work by Stanislav Fomichev <sdf@fomichev.me>. A lot of the meat
of the implementation came from devmem TCP RFC v1[1], which included the
TX path, but Stan did all the rebasing on top of netmem/net_iov.
Cc: Stanislav Fomichev <sdf@fomichev.me>
Signed-off-by: Kaiyuan Zhang <kaiyuanz@google.com>
Signed-off-by: Mina Almasry <almasrymina@google.com>
Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20250508004830.4100853-5-almasrymina@google.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Johannes Berg says:
====================
wireless features, notably
* stack
- free SKBTX_WIFI_STATUS flag
- fixes for VLAN multicast in multi-link
- improve codel parameters (revert some old twiddling)
* ath12k
- Enable AHB support for IPQ5332.
- Add monitor interface support to QCN9274.
- Add MLO support to WCN7850.
- Add 802.11d scan offload support to WCN7850.
* ath11k
- Restore hibernation support
* iwlwifi
- EMLSR on two 5 GHz links
* mwifiex
- cleanups/refactoring
along with many other small features/cleanups
* tag 'wireless-next-2025-05-06' of https://git.kernel.org/pub/scm/linux/kernel/git/wireless/wireless-next: (177 commits)
Revert "wifi: iwlwifi: clean up config macro"
wifi: iwlwifi: move phy_filters to fw_runtime
wifi: iwlwifi: pcie: make sure to lock rxq->read
wifi: iwlwifi: add definitions for iwl_mac_power_cmd version 2
wifi: iwlwifi: clean up config macro
wifi: iwlwifi: mld: simplify iwl_mld_rx_fill_status()
wifi: iwlwifi: mld: rx: simplify channel handling
wifi: iwlwifi: clean up band in RX metadata
wifi: iwlwifi: mld: skip unknown FW channel load values
wifi: iwlwifi: define API for external FSEQ images
wifi: iwlwifi: mld: allow EMLSR on separated 5 GHz subbands
wifi: iwlwifi: mld: use cfg80211_chandef_get_width()
wifi: iwlwifi: mld: fix iwl_mld_emlsr_disallowed_with_link() return
wifi: iwlwifi: mld: clarify variable type
wifi: iwlwifi: pcie: add support for the reset handshake in MSI
wifi: mac80211_hwsim: Prevent tsf from setting if beacon is disabled
wifi: mac80211: restructure tx profile retrieval for MLO MBSSID
wifi: nl80211: add link id of transmitted profile for MLO MBSSID
wifi: ieee80211: Add helpers to fetch EMLSR delay and timeout values
wifi: mac80211: update ML STA with EML capabilities
...
====================
Link: https://patch.msgid.link/20250506174656.119970-3-johannes@sipsolutions.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
